The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index; 5 of the 14 sources its claims cite were checked for support.
TuckER: Tensor Factorization for Knowledge Graph Completion
Open accessAbstract
Ivana Balazevic, Carl Allen, Timothy Hospedales. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
TuckER is a linear link-prediction model based on Tucker decomposition of the binary knowledge-graph tensor, using a shared core tensor and entity/relation embeddings. It achieves state-of-the-art results on standard datasets, is fully expressive, and subsumes several prior linear models as special cases.
Key findings
- TuckER reaches state-of-the-art link prediction results on WN18RR (MRR .470, Hits@10 .526, Hits@3 .482, Hits@1 .443) and FB15k-237 (MRR .358, Hits@10 .544, Hits@3 .394, Hits@1 .266), and on WN18 (MRR .953, Hits@10 .958, Hits@3 .955, Hits@1 .949) and FB15k (MRR .795, Hits@10 .892, Hits@3 .833, Hits@1 .741), apart from Hits@10 on WN18 where R-GCN does better.
- TuckER is fully expressive: Theorem 1 gives a sufficient bound of entity embedding dimensionality \(d_e = n_e\) and relation embedding dimensionality \(d_r = n_r\).
- RESCAL, DistMult, ComplEx, and SimplE can be viewed as special cases of TuckER.
- Parameter sharing through the core tensor helps: on WN18RR TuckER uses ∼9.4M parameters versus ∼16.4M for ComplEx and SimplE at \(d_e=200, d_r=30\); at embedding size 20 (∼300k parameters), TuckER is almost as good as ComplEx and SimplE at embedding size 200 (∼6M parameters), and on FB15k it improves Hits@1 by +14% over ComplEx and +8% over SimplE.
Methods
- TuckER factorizes the third-order binary tensor of triples with Tucker decomposition, scoring \(\phi(e_s, r, e_o) = W \times_1 e_s \times_2 w_r \times_3 e_o\), where \(W\) is a core tensor and subject/object entity embeddings are shared; a logistic sigmoid converts scores to probabilities.
- Training uses reciprocal relations, 1-N scoring, Bernoulli negative log-likelihood, Adam with batch size 128, and random-search hyperparameters; evaluation uses the filtered setting with MRR and Hits@k on FB15k, FB15k-237, WN18, and WN18RR.
- Theoretical analysis proves full expressiveness, derives the dimensionality bound, and shows the relationship between TuckER and prior linear tensor-factorization models.
Limitations
- The paper states future work might include exploring how to incorporate background knowledge on individual relation properties; it does not present a dedicated limitations section.
- Evident from the text: evaluation is limited to four standard link-prediction datasets and MRR/Hits@k metrics, with no broader task or computational-efficiency analysis beyond parameter counts.
- Evident from the text: the full-expressiveness bound \(d_e = n_e, d_r = n_r\) is theoretical and may be much larger than practical embedding sizes; the authors expect smaller dimensionalities to suffice in practice.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
5 of 14 cited sources checked · 3 supported · 0 flagged · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“The authors show that convolution is a way of introducing sparsity and parameter tying and that HypER can be understood in terms of tensor factorization up to a non-linearity, thus placing HypER closer to the well established family of factorization models.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 1 Introduction
What the sources say
- Supportedcites Balažević et al., 2019 source
Section 4.2 (p. 6) describes HypER as tensor multiplication with a constrained core tensor and notes that ReLU is applied before the final dot product. The Related Work section (p. 3) explicitly identifies that ReLU non-linearity as the key difference from existing factorization approaches and describes convolution as multiplication by a sparse tensor with tied weights. (LLM, conf=0.94)
Strength:boosted· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“They further prove other models are not fully expressive: DistMult, because it cannot model asymmetric relations; and transitive models such as TransE (Bordes et al., 2013) and its variants FTransE (Feng et al., 2016) and STransE (Nguyen et al., 2016), because of certain contradictions that they impose between different relation types.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.1 Full Expressiveness and Embedding Dimensionality
What the sources say
- Not matchedcites Bordes et al., 2013
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Feng et al., 2016
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Nguyen et al., 2016 source
The citation immediately following “STransE” identifies the model, rather than attributing the citing authors’ expressiveness proof to Nguyen et al. The source’s model description (SE section; page unavailable) explicitly introduces STransE. It does not establish the claimed contradictions, but that proof is framed as the citing authors’ own. (LLM, conf=0.91)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To our knowledge, ComplEx-N3 (Lacroix et al., 2018) is the only other linear link prediction model that benefits from multitask learning.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
What the sources say
- Partly supportedcites Lacroix et al., 2018 sourceExperimental — accuracy not yet measured
The Experimental Setup (p. 7) identifies ComplEx-N3, and the Introduction (pp. 1–2) reports performance gains for ComplEx from modeling inverse predicates and, on harder datasets, from N3 regularization. Our copy does not establish that ComplEx-N3 benefits from multitask learning or that it is the only other linear link-prediction model to do so. (LLM, conf=0.78)
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“There, rank regularization of the embedding matrices is used to encourage a lowrank factorization, thus forcing parameter sharing between relations.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
What the sources say
- Partly supportedcites Lacroix et al., 2018 sourceExperimental — accuracy not yet measured
Section 4 (p. 4) confirms that the paper proposes nuclear 3-norm regularization for tensor-factorization models, including ComplEx. But it does not say that this regularizer forces parameter sharing between relations; Section 2.2 (p. 2) instead describes ComplEx’s parameter sharing as occurring between the subject and object modes. (LLM, conf=0.84)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Partly supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“TuckER outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models.”
- Also stated in: § 1 Introduction · plain
“proposing TuckER, a new linear model for link prediction on knowledge graphs, that is simple, expressive and achieves state-of-theart results across all standard datasets”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- The authors state this as an assumption: Subject and object entity embedding matrices are equivalent, i.e. no distinction is made between the embeddings of an entity depending on whether it appears as a subject or as an object.
- Also stated in: § 1 Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is supported by the fact that the margin by which TuckER outperforms other linear models is notably increased on datasets with a large number of relations.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Even with fewer parameters than ComplEx and SimplE at d e = 200 and d r = 30 on WN18RR (∼9.4 vs ∼16.4 million), TuckER consistently obtains better results than any of those models.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can see that the difference between the MRRs of ComplEx, SimplE and TuckER is approximately constant for embedding sizes 100 and 200.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.4 Influence of Parameter Sharing
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, running their model with equivalent parameter number to TuckER shows comparable performance, supporting our belief that the two models both attain the benefits of multi-task learning, although by different means.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is important to note that at embedding dimensionalities 20, 50 and 100, TuckER has fewer parameters than Com-plEx and SimplE (e.g.ComplEx and SimplE have ∼3 million and TuckER has ∼2.5 million parameters for embedding dimensionality 100).”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.4 Influence of Parameter Sharing
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- Probably not a substantial claim. 9
- It may state two separate claims as one. 9
Every source the paper cites for this claim was checked and supports it.
In the paper
“As shown in (Trouillon et al., 2017), ComplEx is fully expressive with the embedding dimensionality bound d e = d r = n e • n r .”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.1 Full Expressiveness and Embedding Dimensionality
What the sources say
- Supportedcites Trouillon et al., 2017 source
Theorem 4 in §3.2 (p. 14) shows that ComplEx can represent arbitrary families of relation matrices using a shared entity embedding matrix and diagonal relation matrices of dimension nm, where n is the number of entities and m the number of relations. It states that the decomposition rank is at most nm, matching the claimed dimensionality bound for entity and relation embeddings. (LLM, conf=0.92)
Strength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, for lower embedding sizes, the dif-ference between MRRs increases by 0.7% for embedding size 50 and by 4.2% for embedding size 20 for ComplEx and by 3% for embedding size 50 and by 9.9% for embedding size 20 for Sim-plE.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.4 Influence of Parameter Sharing
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results achieved by TuckER are not only better than those of other linear models, such as DistMult, ComplEx and SimplE, but also better than the results of many more complex deep neural network and reinforcement learning architectures, e.g.R-GCN, MINERVA, ConvE and HypER, demonstrating the expressive power of linear models and supporting our claim that simple linear models should serve as a”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall, TuckER outperforms previous state-of-the-art models on all metrics across all datasets (apart from hits@10 on WN18 where a non-linear model, R-GCN, does better).”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, improvement on FB15k is +14% over ComplEx and +8% over SimplE on the toughest hits@1 metric.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.3 Link Prediction Results
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is trivial to show that both RESCAL and DistMult belong to the family of bilinear models.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.2 Relation to Previous Linear Models
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“It is interesting to note that the TuckER interpretation of the DistMult scoring function, given that matrices A and C are identical, can alternatively be interpreted as a special case of CP decomposition (Hitchcock, 1927), since Tucker decomposition with a superdiagonal core tensor is equivalent to CP decomposition.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.2 Relation to Previous Linear Models
What the sources say
- Not checked — no full text of the sourcecites Hitchcock, 1927 source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We show that TuckER is a fully expressive model, derive sufficient bounds on its embedding dimensionalities and demonstrate that several previously introduced linear models can be viewed as special cases of TuckER.”
- Also stated in: § 1 Introduction · plain
“Finally, we show that several previous stateof-the-art linear models, RESCAL (Nickel et al., 2011), DistMult (Yang et al., 2015), ComplEx (Trouillon et al., 2016) and SimplE (Kazemi and Poole, 2018), are special cases of TuckER.”
- Also stated in: § 1 Introduction · plain
“showing how TuckER subsumes several previously proposed tensor factorization approaches to link prediction.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- The authors state this as an assumption: Subject and object entity embedding matrices are equivalent, i.e. no distinction is made between the embeddings of an entity depending on whether it appears as a subject or as an object.
- Also stated in: § 1 Introduction · plain
In the paper
“Similarly to Com-plEx, Kazemi and Poole (2018) show that SimplE is fully expressive with entity and relation embeddings of size d e = d r = min(n e • n r , γ + 1), where γ represents the number of true facts.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.1 Full Expressiveness and Embedding Dimensionality
What the sources say
- Not matchedcites Kazemi and Poole (2018)
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“So far, there have been two possible ways in which linear link prediction models introduce asymmetry into factorization of the binary tensor of triples: • distinct (although possibly related) embeddings for subject and object entities and a diagonal matrix (or equivalently a vector) for each relation, as is the case with models such as ComplEx and SimplE; or • equivalent subject and object entity”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.3 Representing Asymmetric Relations
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We use evaluation metrics standard across the link prediction literature: mean reciprocal rank (MRR) and hits@k, k ∈ {1, 3, 10}.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.2 Implementation and Experiments
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“TuckER overcomes this by representing relations as vectors w r , which makes the parameter number grow linearly with the number of relations, while still keeping the desirable property of allowing relations to be asymmetric”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 5.3 Representing Asymmetric Relations
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: The full rank matrix approach for relations often leads to overfitting, especially for relations with a small number of training triples.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To test this, we re-implement ComplEx and SimplE with reciprocal relations, 1-N scoring, batch normalization and dropout for fair comparison, perform random search to choose best hyper-parameters”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.4 Influence of Parameter Sharing
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“TuckER achieves state-of-the-art results on standard link prediction datasets, in part due to its ability to perform multi-task learning across relations.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 7 Conclusion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“We use the filtered setting (Bordes et al., 2013), i.e. all known true triples are removed from the candidate set except for the current test triple.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.2 Implementation and Experiments
What the sources say
- Not matchedcites Bordes et al., 2013
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We choose all hyper-parameters by random search based on validation set performance.”
§ TuckER: Tensor Factorization for Knowledge Graph Completion > 6.2 Implementation and Experiments
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
Knowledge graphs typically contain only a small subset of all possible facts.
“However, they typically contain only a small subset of all possible facts.”
“However, far from all available information is currently stored in existing knowledge graphs”
The paper relies on this without support.
Manually adding new information to knowledge graphs is costly.
“and manually adding new information is costly”
The authors state this as an assumption.
Subject and object entity embedding matrices are equivalent, i.e. no distinction is made between the embeddings of an entity depending on whether it appears as a subject or as an object.
“Subject and object entity embedding matrices are assumed equivalent, i.e. we make no distinction between the embeddings of an entity depending on whether it appears as a subject or as an object in a particular triple.”
The paper relies on this without support.
The full rank matrix approach for relations often leads to overfitting, especially for relations with a small number of training triples.
“which often leads to overfitting, especially for relations with a small number of training triples.”
The authors state this as an assumption.
TuckER should need a lower number of parameters for obtaining good results than ComplEx or SimplE.
“The ability of knowledge sharing through the core tensor suggests that TuckER should need a lower number of parameters for obtaining good results than ComplEx or SimplE.”
“which supports our initial assumption.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
RESCAL parameter count squares the wrong dimension
MinorTable 1 gives RESCAL a term proportional to the square of the relation embedding dimension, d_r, but the paper describes a d_e × d_e matrix for each relation. That description implies a term proportional to the square of d_e instead.
“RESCAL (Nickel et al., 2011) e s W r e o W r ∈ R de 2 O(n e d e + n r d 2 r )”
“the relation matrices W r ∈ R de×de are the d e × d e slices of the core tensor Z.”
The core tensor has conflicting dimension orders
MinorTable 1 gives the TuckER core tensor dimensions as entity × entity × relation, whereas the model definition gives entity × relation × entity. These orders differ when entity and relation embedding dimensions differ, as they do for WN18 and WN18RR.
“W ∈ R de×de×dr is the core tensor of a Tucker decomposition.”
“w r ∈ R dr the rows of R representing the relation embedding vector and W ∈ R de×dr×de is the core tensor.”
TuckER does not outperform HypER on WN18 hits@3
MinorThe results table reports the same WN18 hits@3 value, .955, for TuckER and HypER. This is a tie, although the text says TuckER outperforms previous models on every metric except WN18 hits@10.
“Overall, TuckER outperforms previous state-of-the-art models on all metrics across all datasets (apart from hits@10 on WN18 where a non-linear model, R-GCN, does better).”
“| HypER (Balažević et al., 2019) | no | .951 | 958 | .955 | .947 | .790 | .885 | .829 | .734 | | SimplE (Kazemi and Poole, 2018) | yes | .942 | .947 | .944 | .939 | .727 | .838 | .773 | .660 | | TuckER (ours) | yes | .953 | .958 | .955 | .949 | .795 | .892 | .833 | .741 |”
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 6
- Antoine Bordes, Nicolas Usunier, Alberto Garcia- Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating Embeddings for Modeling Multi- relational Data. In Advances in Neural Information Processing Systems.
- Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishna- murthy, Alex Smola, and Andrew McCallum. 2018. Go for a Walk and Arrive at the Answer: Reason- ing over Paths in Knowledge Bases Using Rein- forcement Learning. In International Conference on Learning Representations.
- Seyed Mehran Kazemi and David Poole. 2018. Sim- plE Embedding for Link Prediction in Knowledge Graphs. In Advances in Neural Information Pro- cessing Systems.
- Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A Three-Way Model for Collective Learning on Multi-Relational Data. In International Conference on Machine Learning.
- Adam Paszke, Sam Gross, Soumith Chintala, Gre- gory Chanan, Edward Yang, Zachary DeVito, Zem- ing Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In NIPS-W.
- Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In International Conference on Learning Representations.
Cited by
Sorted by citations
Items 501–600 of 699
Wang, Y., Zhu, X., Chen, T., & Zhang, Y. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00042 · Cited by 1
“To tackle this challenge, a multitude of Knowledge Graph Completion (KGC) techniques have been conceived [2] [3] [1], predominantly employing low-dimensional graph embeddings as a means to modeling the intricate representations of entities and relationships.”
Research on the Knowledge Graph Embedding for Rail Fault Text Based on Translation Model
Cai, Y. M., & Su, S. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865723 · Cited by 1
“Within the realm of knowledge graph embedding models, translation models[3–6] have the highest computational effi-ciency, semantic models [7, 8] are better at handling complex semantic information, and neural network models[9–11] are more effective at uncovering structural information and implicit…”
DGE-ASR: Two-view Graph Neural Networks for Knowledge Graph Completion
Kong, X., Hu, F., Song, Y., & Wang, X. (2024) · International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) · doi:10.1109/icairc64177.2024.10900328 · Cited by 1
“The DGE-ASR model is implemented using PyTorch [13], with parameter initialization performed using the standard Glorot initialization method [14].”
Relation prediction in knowledge graphs: A self-organizing neural network approach
Subagdja, B., Shanthoshigaa, D., & Tan, A. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107679 · Cited by 1
Chen, Y., Duan, X., & Guo, Y. Q. (2025) · Applied Sciences · doi:10.3390/app15137282 · Cited by 1
Hierarchical Blockmodeling for Knowledge Graphs
Pietrasik, M., Reformat, M., & Wilbik, A. (2025) · Semantic Web · doi:10.1177/22104968251377338 · Cited by 2
“Bilinear methods (Balaževi´c et al., 2019; Kazemi & Poole, 2018; Nickel et al., 2011; Yang et al., 2015) operate on the binary adjacency tensor of the knowledge graph and factorize entities and relations into vectors and matrices.”
Multi-Agent Knowledge Graph Question Answering Framework Based on Lightweight Large Language Model
Zhang, D., Yang, S., Fu, B., & Chen, S. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189149
“Users can retrieve and answer questions based on the triple format [2] or textual knowledge within the knowledge graph.”
Knowledge Graph Embedding Based on Hyperplane and Quantitative Credibility
Chen, S., Qiao, L., Liu, B., et al. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-32388-2_50 · Cited by 1
“At present, the knowledge graph indicates that there are two main categories of learning: one is the representation learning method based on tensor decomposition, and the most representative ones are RASCAL [1], DistMult [2], HoIT [3] and TuckER [4].”
3D Learning and Reasoning in Link Prediction Over Knowledge Graphs
Nayyeri, M., Alam, M. M., Lehmann, J., & Vahdati, S. (2020) · IEEE Access · doi:10.1109/access.2020.3034183 · Cited by 1
“Among the semantic-matching models, QuatE [37], TuckEr [2], RESCAL [23], ComplEx [31], DisMult [35] and HolE [22] measure plausibility of edges by matching latent semantics.”
BackgroundMethodResultInfluentialLiu, Y., Liu, J., Long, Z., et al. (2021) · Springer eBooks · doi:10.1007/978-3-030-74386-4_4 · Cited by 1
Xi, J., Miao, Z., & Huang, Q. (2021) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei53629.2021.9624351 · Cited by 1
A Framework for Knowledge-Derived Query Suggestions
Rezayi, S., Lipka, N., Vinay, V., et al. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671344 · Cited by 1
“Most link prediction methods for knowledge graph are based on proximity/distance in the graph, and leverage paths [29], tensor factorization [44], random walks [45], and other local proximity-based mechanisms [43].”
BackgroundLe, T., Tran, C., Tran, L., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10983-6_47 · Cited by 1
IPPT4KRL: Iterative Post-Processing Transfer for Knowledge Representation Learning
Zhang, W., Şerban, O., Sun, J., et al. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5010004 · Cited by 1
Liu, Y., Ren, Z., Liu, X., Wang, X., Wang, Y., & Wang, H. (2024) · Research Square · doi:10.21203/rs.3.rs-4489200/v1 · Cited by 1
Argument Mining on Clinical Trials
Mayer, T. (2020) · theses.fr (ABES) · doi:10.70675/8c2cf7b5z08cbz40e4za421z0115aa4a8eaa · Cited by 1
Machine learning techniques for automatic knowledge graph completion
Boschin, A. (2023) · theses.fr (ABES) · doi:10.70675/16b1d6d1z0e55z4f40z8db6zea0aed15a6a8 · Cited by 1
Online Knowledge Learning Model Based on Gravitational Field Theory
Ji, W., Jiang, T., Wang, M., Tang, X., Chen, G., & Yang, S. L. (2019) · Applied Sciences · doi:10.3390/app9153195
Incorporating Entity Type Information into Knowledge Representation Learning
Huang, W., Wang, G., Zhang, H., & Chen, F. (2020) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc50466.2020.00023
“We use ConvE [11] and TuckER [10] as the baseline models and apply TPPA on them.”
MethodInfluentialSequence Embedding for Zero or Low Resource Knowledge Graph Completion
Du, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-73194-6_20
Overview of Knowledge Graph Completion Algorithms Based on Representation Learning
Zhou, Y., Feng, J., Yang, Z., & Wang, H. (2021) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda51879.2021.9442554
“TuckER [12] is a linear model based on the Tucker decomposition of binary tensors.”
MethodFinding Latent Relationships from Auxiliary Information for Tensor Completion
Zou, Y., An, C., & Qiu, D. (2021) · IEEE International Conference on Big Data and Artificial Intelligence (BDAI) · doi:10.1109/bdai52447.2021.9515213
Shi, Y., Hao, K., Tang, X., & Wang, T. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-1253-5_10
Triple-as-Node Knowledge Graph and Its Embeddings
Lv, X., Shi, J., Cao, S., Hou, L., & Li, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-00123-9_8 · Cited by 1
Knowledge Inference Algorithm Based on Combination of Structure and Context
刘, 明. (2022) · Computer Science and Application · doi:10.12677/csa.2022.123061
Attention-based Learning for Multiple Relation Patterns in Knowledge Graph Embedding
Song, T., & Luo, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-10983-6_50
Zero-Shot Knowledge Graph Completion for Recommendation System
Wang, Z., Chen, C., & Tang, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21753-1_19
Learning Knowledge Graph Embedding with Batch Circle Loss
Wu, Y., Huang, W., Hui, S., & Wang, J. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892213
“ConvE [7], TuckER [13] use the binary cross-entropy loss to train the model.”
MethodA Link Prediction Model Based on Improved TuckER Decomposition and Neural Tensor Network
Zhang, J., Qian, X., & Liu, P. (2022) · International Conference on Data Science and Information Technology (DSIT) · doi:10.1109/dsit55514.2022.9943950
“According to the literature [20], this paper sets the best combination of learning rate and learning rate decay as: the best combination on WN18RR is (0.01,0.99) , and the best combination on FB15K-237 is (0.005,1.0) .”
BackgroundMethodInfluentialSemantic Reasoning Technology on Temporal Knowledge Graph
Li, J., Zhao, F., & Jin, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20309-1_10
Hypernode: Entity Fusion for Data Traceability and Link Prediction
Dong, B., Zhang, Z., Li, J., Zhu, Y. Q., Bu, C., & Wu, X. (2022) · Proceedings · doi:10.1109/icdm54844.2022.00021
“• TuckER [29].”
HTransE: Hybrid Translation-based Embedding for Knowledge Graphs
Shah, A., Molokwu, B. C., & Kobti, Z. (2022) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg55886.2022.00037
“TuckER [23]: TuckER is based on TuckER decomposition [31].”
BackgroundMethodA Convolution Quaternion-Based Inverse Relational Rotation Embedding Knowledge Representation Method
Wu, D., Jing, Z., & Li, M. (2022) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa54385.2022.10032387
“fr(h, t) = concat(g([h, r, t] ∗ Ω)) ·W (4)”
BackgroundPOSE: A Positional Embedding Model for Knowledge Hypergraph Link Prediction
Chen, Z., Wang, X., Wang, C., & Li, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25198-6_25
Relation Heterogeneous Graph Neural Network
Jielin, Y., & Zukuan, W. (2022) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip56608.2022.10016506
“We choose the linear eigenvector as the edge feature and TuckER [17] which has better performance than Distmult as the scoring function.”
MethodKnowledge Graph Representation Learning via Generated Descriptions
Hu, M., Lin, Z., & Marshall, A. H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35320-8_26
Query-Specific Temporal Knowledge Graph Representation Learning Model
Zuo, Y., Liu, Z., Zhou, Y., Zhan, M., & Zhan, P. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00190
“Other models include factorization model [15], neural network model [16] and Transformer-based model [17].”
MethodNELLIE: Never-Ending Linking for Linked Open Data
Ahmed, A. F., Sherif, M. A., & Ngomo, A.-C. N. (2023) · IEEE Access · doi:10.1109/access.2023.3300694
“We used hyper-parameters from [14].”
BackgroundMethodInfluentialSimple Knowledge Graph Completion Model Based on Differential Negative Sampling and Prompt Learning
Duan, L., Wang, J., Luo, B., & Sun, Q. (2023) · Information · doi:10.3390/info14080450
Zhang, H., She, J., Wang, Y., et al. (2023) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1117/12.3004685
“TuckER [15], a Tucker vector decomposition-based linear model, demonstrates good prediction and inference performance on entity prediction tasks.”
A Fact-Searching and Matching System Based on News Content About COVID-19
Jianyang, L., Junrong, B., Bingjin, L., et al. (2023) · ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter) · doi:10.1109/snpd-winter57765.2023.10224054
Multitask Graph Neural Network for Knowledge Graph Link Prediction
Wang, Y., Yang, J., Li, L., et al. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-5971-6_23
LGHAE: Local and Global Hyper-relation Aggregation Embedding for Link Prediction
Yuan, P., Qi, Z., Sun, H., & Liu, C. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-5971-6_26
Knowledge Graph Embedding with Relation Rotation and Entity Adjustment by Quaternions
Sun, W. X., Wu, Q., Wang, X., Yao, J., & Bao, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46674-8_32
Embedding Entity and Relation for Knowledge Graph by Probability Directed Graph
Yang, C., Song, X., Luo, Y., & Zhang, L. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8126-7_4
Hyper-Relational Knowledge Graph Embedding Based on Type Constraints
Wang, C., Li, X., Gan, T., et al. (2023) · International Conference on Advanced Computer Theory and Engineering · doi:10.1109/icacte59887.2023.10335227
“Based on TuckER[15], the GETD[16] model decomposes the higher-order tensor representation of facts in the knowledge hypergraph into a kernel tensor plus several factor matrices and multiplies the nuclear tensor obtained by decomposition with the embedded representation of relations and entities to obtain a rationality…”
MethodRarKGQA: Multi-hop Question and Answering Method Based on Knowledge Graph Embedding
Fangri, R., Altenbek, G., Ma, Y., & Haisa, G. (2023) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml59573.2023.10348187
“Early fusion models, such as GRAFT-Net [19], used a retrieval method with heuristic rules in extracting subgraphs; the method was not intelligent and produced subgraphs that were irrelevant to the answer.”
BackgroundMethodDomain Information Learning For Multi-Domain Knowledge Graph Link Prediction
Zhao, Y., Chao, K., & Li, Y. (2023) · IEEE International Conference on e-Business Engineering (ICEBE) · doi:10.1109/icebe59045.2023.00023
Ghanem, H., & Cruz, C. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-53468-3_35
A novel Knowledge Graph recommendation algorithm based on Graph Convolutional Network
Guo, H., Yang, C., Zhou, L., & Wei, S. (2024) · Connection Science · doi:10.1080/09540091.2024.2327441
“MuRP (Balažević et al., 2019c) learns relation-specific parameters by transforming entity embeddings through Mobius matrix-vector multiplication and Mobius addition.”
Tian, X. L., & Meng, Y. (2024) · Algorithms · doi:10.3390/a17030129
A semantic guide‐based embedding method for knowledge graph completion
Zhang, J., Shen, B., Wang, T., & Zhong, Y. (2024) · Expert Systems · doi:10.1111/exsy.13584 · Cited by 1
Tian, X., & Meng, Y. (2024) · Applied Sciences · doi:10.3390/app14073122 · Cited by 3
Knowledge Graph Embedding Based Graph Convolutional Network for Link Prediction
Wu, Q., & He, Q. (2023) · International Conference on Advanced Cloud and Big Data · doi:10.1109/cbd63341.2023.00050
“TuckER [19] applies Tucker decomposition to binary knowledge triple representations, yielding a simple yet robust linear model.”
MethodPredicting Links in Knowledge Graphs With the Canonical Correlation Analysis and Fusing Tensor Model
Wu, T., Mai, S., Chen, D., et al. (2024) · Computing in Science & Engineering · doi:10.1109/mcse.2024.3397894
Instance type completion in equipment knowledge graph based on translation model
Miao, L., Wu, Y., & Yang, Q. (2024) · Advances in Complex Systems · doi:10.1142/s1793962324500351
Structure-Augment based Long-Tailed Knowledge Graph Completion Model
Wang, J., Tang, Y., Hou, D., Wang, J., Meng, Z., & Xu, T. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580212 · Cited by 1
“[24] .436 .500 .564 3472 .481 RotatE [17] .428 .492 .571 3340 .476 TuckER [25] .443 .482 .526 - .470 ATTH [26] .443 .499 .573 - .486 KG-BERT [27] .410 .302 .524 97 .216 StAR [28] .”
Optimize Rule Mining Based on Constraint Learning in Knowledge Graph
Cai, K., Wang, X., & Luo, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5498-4_7
Research on Information Fusion Representation Learning Method Based on BERT
Yang, F., Du, H., Liu, Z., et al. (2024) · doi:10.1145/3686424.3686450
“In addition, although models such as SimplE [2] and TuckER [3] attempt to incorporate attribute information, they have not yet been able to effectively deal with the complexity and diversity of attributes, limiting the representational capabilities of knowledge graphs.”
Attentional Neural Integral Equation for Temporal Knowledge Graph Forecasting
Xiao, L., Chen, Z., Zhang, R., & Chen, J. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679876
Constructing and Evaluating a Japanese Entity Linking Model for Wikidata based on Pointer Network
Sawamura, Y., Morita, T., Egami, S., et al. (2024) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.39-6_c-o42
RGembed: A Knowledge Graph Embedding Model Integrating Dual-Prediction andGraph Attention Networks
Ma, X., Zhou, X., & Rong, X. (2024) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc63215.2024.10748257
Embedding Hierarchical Tree Structure of Concepts in Knowledge Graph Embedding
Yu, J., Zhang, C., Hu, Z., & Ji, Y. (2024) · Electronics · doi:10.3390/electronics13224486
Enhancing Relationship Link Prediction With Hierarchical Feature Enhancement
Xu, Z., & Wang, H. (2024) · IEEE Access · doi:10.1109/access.2024.3503675
Cheng, K., & Sun, Y. (2024) · Synthesis lectures on data, semantics and knowledge · doi:10.1007/978-3-031-72008-6_3
Temporal relevance for representing learning over temporal knowledge graphs
Song, B., Amouzouvi, K., Xu, C., Wang, M., Lehmann, J., & Vahdati, S. (2024) · Semantic Web · doi:10.3233/sw-243699
DSparsE: Dynamic Sparse Embedding for Knowledge Graph Completion
Yang, C., Li, B., & Wu, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78183-4_9
Enhancing Knowledge Graph Completion by Extracting Potential Positive Examples
Xing, S., Yilahun, H., & Hamdulla, A. (2024) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml62565.2024.10779715
An original model for multi-target learning of logical rules for knowledge graph reasoning
Li, H., Wang, B., Wang, K., Zhang, R., & Wei, Y. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05966-1 · Cited by 1
“We select several prominent embedding-based algorithms for comparison, including TransE [4], DistMult [42], TuckER [2], RotatE [35], ConvE [6], QuatDE [9] and KNN-KG [39].”
Chen, B., Li, H., & Shi, Z. (2024) · Mathematics · doi:10.3390/math13010068
Relational message passing with mutual information maximization for inductive link prediction
Liang, X., Si, G., Li, J., et al. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-024-06749-8
“Tensor factorization models, including DistMult [16], ComplEx [23], and TuckER [24], represent KGs as three-dimensional tensors, focusing on latent semantics.”
Relational Clustering-Based Parallel Spaces Construction and Embedding for Dynamic Knowledge Graph
Liu, Y., & Zhang, Y. (2025) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3527238
“(cid:2) TuckER [29] is a linear model based on the Tucker decomposition of the binary tensor representation of knowledge graph triples.”
Harmonizing Human Insights and AI Precision: Hand in Hand for Advancing Knowledge Graph Task
Wang, S., Zhang, Y., Huang, X., & Wang, H. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831002
“…of all kinds, and they can be categorized into three main types based on the architecture [6], which are geometric models (e.g. TransE [3], TransH [29], RotatE [30]), tensor factorization models (e.g. DistMult [31], TuckER [32]), deep learning models (e.g. ConvE [33], KBGAT [34], MoCoSA [35]).”
Ding, L., Zhao, J., Lü, K., & Hao, Z. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831161
PARALLAX: Leveraging Polarization Knowledge for Misinformation Detection
Paschalides, D., Pallis, G., & Dikaiakos, M. D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78541-2_6
A Relation Semantic Enhancement Method for Large Language Model Based Knowledge Graph Completion
Si, J., Ouyang, X., Zhu, X., & Zhang, Y. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00035
“Additionally, we include comparisons with traditional structure-based KGC models, like TransE [25], TransH [26], TransR [27], DKRL [18], TransT [17], DistMult [28], RotatE [29], TuckER [30], TransC [31]) and HAKE [32], to provide a comprehensive assessment of our framework’s performance.”
InfluentialWu, P., & Liu, J. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865299
Li, R., Tu, J., Wu, S., Hu, F., & Ma, L. (2024) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei63587.2024.10871239
How to Decide Like Human? A Commonsense-Aware Hierarchical Framework for Knowledge Graph Reasoning
Xia, Y., Zhou, G., Luo, J., Lan, M., & Huang, N. (2025) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3544126
“We compare with embedding-based models, i.e., Com-plEx [41], RotateE [7], TuckER [42], ConE [43], and NBFNet [23].”
DcKE: A Dual Encoder-decoder Knowledge Embedding Model for Link Prediction
Lin, J., Ren, X., Li, X., et al. (2024) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa63168.2024.00043
“[14], TuckER [15], and QuatE [16]; semantic matching models such as DistMult [17] and ComplEx [18]; CNN-based models like ConvE [6] and JointE [7]; GNN-based models such as R-GCN [9] and CompGCN [10]; and Transformer-based models like LP-BERT [11] and N-MlpE [19].”
InfluentialDA-HFA: Knowledge Graph Completion Based on Data Augmentation and Hierarchical Feature Aggregation
Zheng, Z., Mao, C., Li, W., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2376-1_21
Multimodal Knowledge Graph Completion Model Based on Modal Hierarchical Fusion
Zhang, S., Huang, H., Lin, X., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2376-1_28
Knowledge Graph Completion with Entity Type-Aware and Deep Feature Extraction
Zhang, F., You, C., Lin, X., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2376-1_29
CPM: Knowledge Graph Tensor Factorisation Model for Discovering Drug Targets
He, C., Yang, C., Li, B., Zhang, H., & Zhao, X. (2024) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei64163.2024.10906268
RoEMF: rotational embedding multimodal fusion for link prediction
Lu, S., Xinqiang, L., Zhang, W., & Tang, H. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02386-6
“(i) single-modal methods that solely rely on structural information for link prediction: TransE [12], ConvE [15], ConvKB [16], CapsE [37], RotatE [18], TuckER [17], HAKE [4], ComplEx [19].”
Enhancing Drug-Drug Interaction Prediction by Knowledge Graph Embedding
Liu, C., Wang, X., & Liu, Q. (2024) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc63072.2024.10935249
“In contrast, similarity-based scoring functions like ANALOGY [20] and TuckER [21] assess the plausibility of facts through semantic matching.”
Including Co-Relation via Concatenate Operator for Static and Temporal Knowledge Graph Embedding
Xiao, L., Zhang, R., Chen, J., & Zhang, L. (2025) · ACM Transactions on Information Systems · doi:10.1145/3733231
“Decomposition-based models such as RESCAL [26], Distmult [45], ComplEx [35], and TuckER [2], utilize tensor factorization to compute the event score.”
InfluentialMining Positive Examples from Negatives for Enhanced Knowledge Graph Completion
Xing, S., Anwer, S., Yilahun, H., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-5123-8_22
GNN-FTuckER: A novel link prediction model for identifying suitable populations for tea varieties
Li, J., Yang, B., Liu, J., Wang, X., Wu, Z., Huang, Q., & He, P. (2025) · PLoS ONE · doi:10.1371/journal.pone.0323315
Training-Free Score Calibration for Complex Query Decomposition
Ott, S., Chekol, M. W., Meilicke, C., & Stuckenschmidt, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-94575-5_11 · Cited by 1
Bridge Structural Knowledge and Pre-trained Language Models for Knowledge Graph Completion
Qiao, Q., Li, Y., Wang, Q., Zhou, K. Q., & Li, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8180-8_31
“…mine the plausibility of a fact by calculating the semantic similarity between entities and relations (Nickel et al., 2011; Yang et al., 2015; Balazevic et al., 2019; Liang et al., 2023); and (3) Neural network-based models, which employ deep neural networks to fuse the graph network…”
A Novel Framework for Multi-hop Reasoning via Alternate Entity and Sequence Generation
Shang, Y., Zhang, W., Li, H., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8180-8_36
An interpretable reasoning schema for fuzzy knowledge graph under interval Type-2 fuzzy model
Li, P., Cheng, G., Zhao, Y., et al. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113534
Dual-context enhanced knowledge representation learning method in hyper-relational knowledge graphs
Li, J., Han, Q., Lu, D., & Li, L. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02003-7
“In addition, tensor decomposition models represent KG as a three-dimensional tensor, and tensors are decomposed into combinations of vectors as embeddings [20, 21].”
Multi-granularity Multimodal Information Interaction for Knowledge Graph Completion
Li, F., Zhu, X., & Hu, Z. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7008-6_6
A Hybrid Graph Contrastive Learning Approach with Negative Sampling for Knowledge Graph Completion
Pan, W., Hua, Q., Zhang, Y., Lu, Y., Chen, J., & Qin, J. (2025) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd64986.2025.11082092
Knowledge Graph Completion Combining Dynamic Learnability and Contrastive Learning
Zhang, X., Zhang, L., Yan, S., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0014-7_40
Entity class-restricted twin attention-based aggregation for geographic knowledge graph inference
Kong, J., He, X., Fang, H., Ji, R., Yang, P., Li, S., Li, H., Sun, H., Qiao, M., Li, P., et al. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02060-y
“Utilizing the Tucker decomposition strategy [30], TuckER [31] models KGs as binary tensors to decompose them, enabling the min-ingofdeepsemanticinteractions.”
Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
Yusupov, V., Rakhuba, M., & Frolov, E. (2025) · doi:10.1145/3705328.3759328
“However, there are relatively few hyperbolic methods that explicitly model ternary item-user-item interactions [36, 37], similarly to Knowledge Graph Completion [3], which limits their ability to fully harness the potential of representation learning.”
Metadata
- Authors
- Balazevic, I., Allen, C., & Hospedales, T.
- Affiliations
- University of Edinburgh (GB)
- Venue
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Published
- 2019
- Pages
- 5184-5193
- OpenAlex
- W2914592219
- Cited by
- 696
- References
- 0
- Citations by year
- 2026: 81 · 2025: 125 · 2024: 165 · 2023: 137 · 2022: 109 · 2021: 55 · 2020: 21 · 2019: 3
- FWCI
- 17.97
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- arXiv (Cornell University) (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- University of Edinburgh
- Engineering and Physical Sciences Research Council (EP/L016427/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Mathematics › Computational Mathematics › Tensor decomposition and applications
- Keywords
- knowledge graph completion, tensor decomposition, Tucker, knowledge graphs
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-23, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-23 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
