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 601–699 of 699
Hyperparameter-Free Bi-level Knowledge Graph Optimization for Link Prediction
Li, H., Mei, T., & Fang, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04549-2_2
Make LLMs Perform Better in Knowledge Graph Completion Combined with RAG
Xu, M., Li, B., Wang, H., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3453-1_12
Guo, L., Sanz-Cruzado, J., & McCreadie, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02899-0_7 · Cited by 1
Are LLMs Really Knowledgeable for Knowledge Graph Completion?
Liu, Y., Sun, Z., Shao, Z., Cui, Y., & Hu, W. P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09530-5_5 · Cited by 1
ProgKGC: Progressive Structure-Enhanced Semantic Framework for Knowledge Graph Completion
Li, Z., Wu, Y., Yuan, Y., & Wang, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09527-5_5 · Cited by 1
Leveraging Open Path from Pruned Graph for Link Prediction on Knowledge Graphs
Liu, X., Lu, Y., & Rao, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-09527-5_30
Li, S.-C., Chen, B., Xin, Y., Cheng, Z.-T., Chen, Q., Zhong, T., & Zhou, F. (2025) · IEEE International Conference on Multimedia and Expo · doi:10.1109/icme59968.2025.11209090 · Cited by 2
Zhang, M., & Chung, W. (2025) · Mathematics · doi:10.3390/math13213486
A Model-Agnostic Approach for Semantically Driven Disambiguation in Human-Robot Interaction
Doğan, F. I., Patel, M., Liu, W., et al. (2025) · IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) · doi:10.1109/ro-man63969.2025.11217614
SAKG: Structure-Aware Large Language Model Framework for Knowledge Graph Reasoning
Zhang, Q., Min, H., Fei, W., et al. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3760893
“Following the hierarchical design, the final input sequence is constructed as: where STRUCT encodes the structural tokens derived from Tucker embeddings, NEIGHBOR contains the selected neighbor information, INST specifies the task instruction, and TEXT(h, r, t) is a natural language representation of the target triple.”
An Ensemble Link Prediction Model for Sparse Knowledge Graphs With Drifting Entity
Zheng, X., Li, P., Zhou, P., & Wu, X. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3628292
“2) Tensor factorization based methods: ComplEx [42], DistMult [18], TuckER [43], ATTH [35], and GIE [19].”
Contextually-Enriched KGC: A Novel Framework for Relational Semantics Enhancement
Lu, F., & Pan, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4094-5_5
Zheng, Z., Cai, B., Xiang, Y., & Sood, K. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228572
“The Tucker decomposition-based model [25] further enriches the expressiveness of entity and relation embeddings in a multidimensional space.”
A Dual Quaternion Embedding Method of Link Prediction based on Orthogonalization and Rotation
Mao, X., Sun, M., Zhang, J., & Wu, K. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228539
Zhang, C.-Y., Liao, X., & Wu, H. (2025) · doi:10.1109/ijcnn64981.2025.11228217
“Tucker decomposition [31-32] further extends this approach by introducing a core tensor that captures latent interactions across different dimensions, making it suitable for analyzing evolving academic collaboration patterns.”
GLAF-KGC: Global-Local Attention Fusion Driven Knowledge Graph Completion Model
Tong, X., & Xu, B. (2025) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa67752.2025.00184
Bidirectional Attention-Enhanced Knowledge Graph Embeddings for Link Prediction
Zhou, D., Yuan, M., & Lin, Y. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11289923
Exploring Multi-aspect Information for Knowledge Graph Completion with Large Language Model
Wang, L., Sheng, J., Zhang, W., Liu, T., & Zhang, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227427
Zuo, Y., Du, J., Kou, F., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-1106-8_10
Image Attribute Completion: A Novel Task for Multi-modal Knowledge Graph
Ma, Y., Zhou, Q., Chen, W., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-3906-2_30
Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
Chen, J. C. J., Zhang, K., Gan, A., Tong, S., Shen, S., & Liu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-3830-0_40 · Cited by 3
KGC-Explainer: Toward Explainable Knowledge Graph Completion
Hou, C., Song, Y., Song, J., Chu, W. C.-C., Fei, X., Li, J., & Lv, H. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2025.3650538
Multimodal Knowledge Graph Completion with Bottleneck Attention and Relation-Aware Representation
Li, F., & Shi, D. (2025) · International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI) · doi:10.1109/mlbdbi67855.2025.11331380
“In contrast, semantic and tensor decomposition methods, including DistMult [5], ComplEx [6], and TuckER [7], represent entity–relation interactions through bilinear or tensor-based scoring functions.”
Multi-Branch Ensemble with Cross-Modal Fusion for Multi-Modal Knowledge Graph Completion
Tian, G., Ning, B., Zhou, X., Zou, W., Yang, R., & Ni, Y. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11323051
“1) Relation Decoder and Score Aggregation: To model the interactions between entities and relations in each modality, we employ the Tucker [7] decomposition as the scoring function.”
Heterogeneous graph structure learning for link prediction in knowledge hypergraphs
Li, D., Li, Z., & Wang, J. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02827-2
“TuckER [29] models knowledge graphs as multi-dimensional tensors and employs Tucker decomposition to capture complex high-order relational patterns, thereby improving prediction accuracy.”
HyperKGC: Hypergraph-Enhanced Multimodal Knowledge Graph Completion with Dynamic Fusion
Chen, H., Yu, X., Li, B., Yin, M., & Jin, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5567-3_10
TransConvE: A Dual-Perspective Framework for Scalable and Efficient Knowledge Graph Embedding
Chen, W., Cao, C., Hu, W., & Zhang, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342577
“Among the embedding-based approaches, TransE [5] and RotatE [27] are included, along with Dist-Mult [16], ComplEx [17], and TuckER [28].”
DNPrune-GT: Graph Transformer with Dynamic Neighbor Pruning for Knowledge Graph Reasoning
Zhang, Q., & Gong, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5696-0_9
Direction-Aware Attentive Hypergraph Learning for Knowledge Graph Completion
Nie, H., Zhao, X., Bi, X. J., Yao, X., Sun, Y., & Lv, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5640-3_5
CSGD: Commonsense Knowledge Graph Completion via Graph Densification and Subgraph Reasoning
Wang, Y., Ma, J., Qu, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5640-3_38
Optimization on the extended tensor-train manifold with shared factors
Molozhavenko, A., & Rakhuba, M. (2026) · Computational and Applied Mathematics · doi:10.1007/s40314-025-03605-0
“In machine learning, for instance, shared factors can model relationships between similar entities: in knowledge graph completion (Balazevic et al. 2019; Peshekhonov et al. 2024), different modes may represent the same entity type, while in recommender systems, duplicated modes can represent…”
MuC: A Multi-core Tucker Model with Core Attention
Zhang, Y., Zhu, D., & Li, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15538-2_40
TRA: Topological Relation-Aware link prediction in spatial knowledge graphs
Zhang, F., Li, Q., Chen, H., et al. (2026) · Earth Science Informatics · doi:10.1007/s12145-025-02068-5
“Tensor decomposition methods represent a KG as a 3D adjacency matrix and attempt to fit this matrix using embed - ding vectors of entities and relations, such as RESCAL (Nickel et al. 2011 ), DistMult (Yang et al. 2015 ), ComplEx (Trouillon et al. 2016 ), and TuckER (Balazevic et al. 2019).”
Investigating the Effects of Negative Sampling in Knowledge Graph Completion
Moon, S., & Ko, Y. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11389098
“TuckEr [9] applies three-way Tucker tensor decomposition to KGC for capturing rich interactions between entities and relations.”
MEDKGC: A Mixture-of-Experts Enhanced Diffusion Model for Multimodal Knowledge Graph Completion
Hou, X., Liang, M., & Huang, W. (2026) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp68355.2026.00057
“The unimodal methods include TransE [5], RotatE [31], ComplEx [38] and TuckER [9].”
Target-Guided Asymmetric Path Modeling in Equipment Maintenance Knowledge Graphs
Chen, M., & Bo, Y. (2026) · Symmetry · doi:10.3390/sym18030439
A Temporal Knowledge Completion Model Driven by Dual-Module for Evolutionary Feature Perception
Xu, T., Song, J., Guo, J., Yu, M., Redouane, A., Kchikach, M., & Zhao, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6426-2_44
Multi-Feature Fusion Strategies for Enhancing Knowledge Graph Embedding
Liu, C., Pu, F., Yang, B., et al. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402131
Retrieval-Reranker: A Two-Stage Pipeline for Knowledge Graph Completion
Gergin, B., & Chelmis, C. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401469
“…• advanced embedding-based models, namely neural network-based (i.e., R-GCN [28] and ConvE [11]) and tensor factorization-based (i.e., TuckER [5]) • ensemble-based models (i.e., SnapE [29] and Cascader [26]), and • methods leveraging large language models (i.e., KG-BERT [43] and StAR [37]).”
Guo, J., Zhao, M., Xu, T., et al. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3666470
“Next, TuckER [13] uses Tucker decomposition features to integrate facts into three member matrices, and uses core tensors to realize the interaction between entities and relations.”
RANA: Conflict Resolution for Knowledge Graphs with Better Representation Learning
Song, Z., Peng, H., Zeng, W., & Zhao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5009-8_9
Gou, J., Zhang, Q., Chen, P., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7075-1_43
Chen, Z., & Yu, L. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00685-8
“– TuckER (Balaževi´c et al. 2019): A tensor factorization approach that has performed well on these benchmarks.”
Neural graph-to-text generation with euclidean and riemannian graph encoding
Montella, S. (2023) · theses.fr (ABES) · doi:10.70675/b0563a9fz0ff1z4daaza710za9e4d3ed4301
Li, J., Han, Q., Zhang, H., & Li, L. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02293-5
“Tensor decomposition models, such as DistMult and TuckER, represent KGs as 3D tensors and decompose them into low-dimensional vectors, offering efficiency but also leading to overfitting [29, 30].”
Happi, B. G. H. (2024) · theses.fr (ABES) · doi:10.70675/20022d2az1be9z4bd9za6e1zb410bde66ce1
Tornés, B. M. (2024) · theses.fr (ABES) · doi:10.70675/62871f27ze532z49a0z93d9z667592544b9c
MELGene: knowledge-enhanced multimodel ensemble learning for disease–gene association prediction
Tian, H., Yang, K., Liu, Z., Gao, H., Yu, J., Zhang, L., & Zho, X. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag172
Time-decay and frequency-domain transformation for temporal knowledge graph completion
Feng, S., Zheng, Y., Liu, Q., et al. (2026) · Intelligent Data Analysis · doi:10.1177/1088467x261436902
Shen, H., Chen, B., Cheng, Z., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462749
ICRe-CoT: A Retrieval-Revised Two-Stage Ranking Framework for LLM-Based Knowledge Graph Completion
Shen, T., Zhang, F., Chen, H., Wu, W., Cheng, J., & Fu, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464337
Dhami, D. S., Mathur, S., Yan, S., et al. (2025) · doi:10.1145/3799830.3799847
Semantically Enhanced Knowledge Graph Reasoning for Emerging Entities
Zhou, X., Guo, Y., Wang, Y., et al. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487684
“Embedding-based models further include tensor decomposition models that decompose high-dimensional tensors into lower-dimensional entity and relation matrices (e.g., RESCAL [1], DistMult[2], Tucker[3]), geometric models that project entity and relation embeddings into a geometric space for reasoning based on spatial d…”
SeSKGC: A Semantic–Structural Fusion Framework for Knowledge Graph Completion
Feng, P., Xu, S., Du, X., Chen, Y., & Dong, Y. (2026) · Symmetry · doi:10.3390/sym18050737
Wang, S., Feng, Y., & Li, M. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-7656-2_14
Xue, Z., Chen, J., Hu, X., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104849
Wang, X., Song, Z., Wang, Z., et al. (2025) · IEEE/ACM International Symposium on Quality of Service (IWQoS) · doi:10.1109/iwqos65803.2025.11506401
“Using a graph embedding model (e.g., TuckER [4]), we project source and target domain nodes into a shared latent space, enabling semantic-aware knowledge alignment.”
Robust Knowledge Graph Embedding via Denoising
Song, T., Ma, X., Liu, Y., Luo, J., & Hoehndorf, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-25156-5_22
Yu, R., Pan, S., Zhao, M., Xu, T., Guo, J., Yu, J., & Yu, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0378-9_18
Hybrid knowledge reasoning over knowledge hypergraph: Inductive, deductive, and abductive
Tian, L., Gao, L., Zhang, B., Liu, X., Shi, Y., & Gao, H. (2026) · Journal of Electronic Science and Technology · doi:10.1016/j.jnlest.2026.100361
A Multi-Layer Knowledge Graph-Driven Conceptual Design Approach for Complex Customized Products
Huo, Y., Li, R., Zhang, H., et al. (2026) · Mechanisms and machine science · doi:10.1007/978-981-95-7342-4_8
Luo, Y., Hu, J., Zhang, G., et al. (2026) · Electronics · doi:10.3390/electronics15112413
Relation Prototype Driven Multimodal Knowledge Graph Completion
Zhu, S., Yan, C., Hou, B., Gao, M., Hong, Q., Yin, D., & Wang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1462-4_43
RLKGC: Reinforcement Learning Retrieval with Large Language Models for Knowledge Graph Completion
Teya, U. B., Shu, K. P., Arslanturk, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1468-6_37
BiRKGC: Bidirectional Relation and Graph-Aware Model for Knowledge Graph Completion
Zhang, Y., Qin, J., Kang, S., Chen, D., Li, H., Zhang, L., & Feng, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7251-9_20
Structure-Semantics Guided Fine-Grained Multimodal Knowledge Graph Completion Method
Xing, H., Fan, H., & Ding, W. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557851
“This paper selects five classic traditional knowledge graph completion methods: TransE[22], DistMult[23], ComplEx[24], RotatE[25], TuckER[26], as well as twelve advanced multimodal knowledge graph completion methods: IKRL[1], TransAE[3], VBKGC[14], OTKGE[27], MMRNS[15], MANS[28], VISTA[29],…”
Rel-LLM: A Filter-then-Rerank Framework for Knowledge Graph Relation Prediction
Zhang, Y. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557697
“We evaluated our proposed method on two standard benchmark datasets: FB15k-237 [6] and NELL-995-h100 [7].”
InfluentialBiomedical knowledge graphs driving new target identification and novel drug discovery
Dou, P., Yang, X., Jiang, Y., Xie, X., Geng, X., Huang, H., Li, H., & Li, S. (2026) · Targetome · doi:10.48130/targetome-0026-0025
TEOKGC: text embedding optimization for knowledge graph completion
Huan, H., & Zhu, T. (2026) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-026-01226-7
Anomaly Detection via Contrastive Learning on Graph using Embedding
Shan, G., Cong, L., Sun, X., et al. (2026) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194026500555
Yang, C., Xiong, F., Luo, Y., & Wang, F. (2026) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2026.3710670
“…for the embedding method comparison experiments, namely, the translation models TransE [42], TransR [43], and TransA [44]; the tensor decomposition models DistMult [45], ComplEx [46], Tucker [47] and CP [48]; deep neural network models ConvE [49], R-GCN [50]; and other types of models RotatE [51].”
Liu, Y., Zheng, S., Zhu, Z., Xu, Y., Zhuang, Y., Zhao, Y., & He, K. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3710321
“TuckER [28] exploits the Tucker tensor decomposition to reverse the entity-relation interaction.”
LLM-Enhanced Multi-granularity Hierarchical Perception in Temporal Knowledge Graph Completion
Wu, C., Feng, S., Xue, S., Wang, L., & Kong, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2494-4_13
Wang, Q., Deng, K., Zhu, L., et al. (2026) · Information Systems · doi:10.1016/j.is.2026.102775
Dynamic Mixture-of-Experts for Multi-modal Knowledge Graph Completion
Zuo, Y., Yao, Z., & Yuan, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3520-9_25
Liu, B., Wang, M., Zhou, J., et al. (2026) · Mathematical Foundations of Computing · doi:10.3934/mfc.2026027
지상준, Kim, S., Lee, Y., Koo, B., Jin, X., & Oh, B. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818000 · Cited by 1
Xiao, Y., Zhou, H., Yang, H., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818829
FLASH: Fast Generative Retrieval via Autoregressive Semantic Hashing with Provably Distance Bounds
Zhang, Y., Zhu, H., Shi, H., Chen, Y., Han, X., Zhang, Y., Song, L., Wang, W., Zhou, C., Shang, X., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817800
“Many information needs are inherently directional—a question should retrieve its answer, but the answer need not retrieve the question; a premise should retrieve its entailment, but not vice versa [4, 7, 37].”
Tensor Methods: A Unified and Interpretable Approach for Material Design
Pakala, S., Gongora, A. E., Giera, B., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3819008
“There are classical methods, relying solely on the tensor factors, such as CPD [15], CPD-S (a CPD-based method that imposes smoothness constraints on some of the tensor factors) [1, 24], and TuckER [4].”
Song, S. H., Lee, J., Chanki, K. I. M., & Chon, K.-W. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00241
RaSE-KGC: A Relation-Aware Segment Encoding Approach for Knowledge Graph Completion
Lin, C., Luo, Y., Liu, K., & Wu, Q. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00223
“Other approaches, including DistMult [23], ComplEx [24], and TuckER [25], extend this idea by using bilinear or tensor decomposition techniques to capture more complex interaction patterns.”
Structure-Guided Fusion Semantic Denoising for Multi-modal Knowledge Graph Completion
Wang, L., Ning, B., Chengfei Liu, A., Zhou, X., Shi, Y., & Ma, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37673-2_24
Chen, H., Liu, C., & Shao, P. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08856-0
“Traditional structured KGC models primarily rely on the geometric or algebraic properties of triples within the graph, such as the algebraic tensor factorization-based TuckER [12] and embedding models based on complex hyperspheres.”
Frequency-Modulated Spiral Manifold: A Model for Temporal Knowledge Graph Completion
You, X., Long, K., Wang, Z., Lu, L., & Zhang, K. (2026) · Mathematics · doi:10.3390/math14173234
Wang, Y., Chen, Y., Ke, W., Zhou, Y., & Dong, Z. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9514-3_9
Zhang, H., Han, Q., Sun, H., Song, H., & Liu, C. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10100323
Multimodal knowledge graph completion method for addressing imbalance of modal information
Tian, R., Yu, H. Z., Geng, Y., et al. (2026) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-026-01272-1
“By referring to the study TuckER (Balažević et al. 2019 ), in MI-MKGC, we fix the batch size to 1024 and set the training epochs to 1000.”
Path-Jaccard: A Logic-Based Similarity Measure for RDF Resources
Schena, V., Colucci, S., Donini, F. M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40774-0_43
Entity-Dependent Relation Learning for Knowledge Graph Completion
Wang, K., Dai, P., Wang, C., et al. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3720279
“…the type of the true tail entity t; (ii) ˆ t ranks among the top 10 predictions by that model; and (iii) the triplet ( h , r , ˆt ) does not present in G. 2) Results Analysis on CODEX: We compare the following embedding methods: RESCAL [16], TransE [8], Com-plEx [26], ConvE [17], and TuckER [49].”
Zhu, J., He, T., Fu, Y., et al. (2026) · doi:10.1109/ijcnn69854.2026.11729744
“In recent years, embedding-based approaches and Graph Neural Network (GNN)-based approaches [2], [3] have achieved significant progress in forecasting tasks by learning low-dimensional representations of entities and relations to capture the structural and temporal evolution patterns of the graph.”
Zhou, Y., & Zhang, Q. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728652
“The triplet plausibility is scored using the Tucker [20] Score (TS) function: where W is a learnable core tensor, and × i denotes the i - mode product between a tensor and a vector.”
DSS: Dynamic Sparse Selection for Multi-modal Knowledge Graph Completion
Zhou, Y., & Zhang, Q. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729066
“Subsequently, we introduce Tucker [16] as our scoring function S ( h, r, t ) = W × 1 (cid:101) h × 2 (cid:101) r × 3 t , where × i denotes the vector product along the i -th mode, and W is a learnable tensor during training.”
SPaR: Instance-Conditioned Routing for Multimodal Knowledge Graph Completion
Ma, X., Yolwas, N., Sun, L., et al. (2026) · doi:10.1109/ijcnn69854.2026.11728812
“We pit SPaR-MoE against ten prior methods: (1) Graph-only : TransE [5] (translation-based), RotatE [8] (rotation in complex plane), TuckER [9] (tensor decomposition); (2) Multimodal : RSME [15] (visual projection), OTKGE [18] (optimal-transport alignment), MoSE [28] (subgraph-conditioned MoE), IMF…”
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
