Convolutional 2D Knowledge Graph Embeddings
Open accessAbstract
Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models — which potentially limits performance. In this work we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree — which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set — however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets — deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models, and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
ConvE is the first model to use the convolutional neural network framework for knowledge graph completion.
“ConvE [22] is the first model to use the convolutional neural network (CNN) framework for KG completion.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [22]
The Related Work section (p. 2) describes ConvE as, to the authors’ knowledge, the first neural link-prediction model to use 2D convolutional layers. The citing sentence drops both the 2D restriction and the authors’ qualification, making a broader priority claim than the source supports. (LLM, conf=0.88)
Experimental — accuracy not yet measuredConvE obtains local relationships in different dimensions between entities through a convolution layer and a fully connected layer, but ignores the global relationships between triple embeddings of the same dimension.
“ConvE obtains local relationships in different dimensions between entities through a convolution layer and a fully connected layer, which ignores the global relationships between triple embeddings of the same dimension.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [22]
The model description (p. 3) says ConvE uses convolutional and fully connected layers to model interactions between entity and relation embeddings. The discussion of 2D convolutions (p. 2) describes interactions between embeddings, but does not say ConvE ignores global relationships between triple embeddings of the same dimension. The Conclusion (p. 7) proposes increasing large-scale structure as future work, which does not establish that specific limitation. (LLM, conf=0.87)
Experimental — accuracy not yet measuredThe third group of KGE models are neural-network-based models, such as ConvE, ConvKB, HypER, CompGCN, SACN and CNN-BiLSTM.
“The third group are neural-networkbased models, such as ConvE [22], ConvKB [23], HypER [24], CompGCN [25], SACN [26] and CNN-BiLSTM [27].”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [22]
ConvE introduces a 1-N scoring program that takes a head-entity-relation pair and matches all tail entities simultaneously, saving much evaluation time.
“Moreover, ConvE introduces a 1-N scoring program that takes a head-entity-relation pair and matches all the tail entities simultaneously, which is different from other models that use the 1-1 scoring program; thus, much evaluation time is saved.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [22]
HypER improves ConvE by a hypernetwork that can perform weight sharing across layers and dynamically synthesize weights given inputs.
“HypER and ConvE [22] are based on a CNN; the former improves the latter by a hypernetwork, which can be used to perform weight sharing across layers and dynamically synthesize weights given inputs.”
From A Survey on Knowledge Graph Embeddings for Link Prediction (2021) · cites this paper as [22]
A simple rule-based model based on inverse relation detection, called Inverse Model, achieves state-of-the-art results in both WN18 and FB15k.
“They demonstrate the severity of said leakage by showing that a simple rule-based model based on inverse relation detection, dubbed Inverse Model, achieves state-of-the-art results in both WN18 and FB15k.”
From Knowledge Graph Embedding for Link Prediction (2021) · cites this paper as [11]
WN18RR was built to be a more challenging dataset than WN18 by applying a pipeline similar to the one employed for FB15k-237.
“To resolve that, they build the far more challenging WN18RR dataset by applying a pipeline similar to the one employed for FB15k-237 [57].”
From Knowledge Graph Embedding for Link Prediction (2021) · cites this paper as [11]
ConvE represents entities and relations as one-dimensional embeddings and uses a convolutional layer followed by a dense layer to compute fact scores.
“ConvE [11] represents entities and relations as one-dimensional 𝑑 -sized embeddings. When computing the score of a fact, it concatenates and reshapes the head and relation embeddings 𝒉 and 𝒓 into a unique input [ 𝒉 ; 𝒓 ] ; we dub the resulting dimensions 𝑑 𝑚 × 𝑑 𝑛 . This input is let through a convolutional layer with a set 𝝎 of 𝑚 × 𝑛 fi lters, and then through a dense layer with 𝑑 neurons and a”
From Knowledge Graph Embedding for Link Prediction (2021) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
Complex Embeddings for Simple Link Prediction
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., & Bouchard, G. (2016) · arXiv · doi:10.48550/arxiv.1606.06357 · Cited by 2,100 · see citing works
Self-citationSTransE: a novel embedding model of entities and relationships in knowledge bases
Nguyen, D. Q., Sirts, K., Qu, L., & Johnson, M. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1054 · Cited by 177 · see citing works
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Flagged first, then by citations
Research works printed but not linked: 28
- Bordes, A.; Usunier, N.; García-Durán, A.; Weston, J.; and Yakhnenko, O. 2013a. Translating Embeddings for Modeling Multi-relational Data. In Proceedings of NIPS , 2787-2795.
- Bordes, A.; Usunier, N.; García-Durán, A.; Weston, J.; and Yakhnenko, O. 2013b. Translating Embeddings for Modeling Multi-relational Data. In Proceedings of NIPS , 2787-2795.
- Bordes, A.; Glorot, X.; Weston, J.; and Bengio, Y. 2014. A semantic matching energy function for learning with multirelational data - application to word-sense disambiguation. Machine Learning 94(2):233-259.
- Bouchard, G.; Singh, S.; and Trouillon, T. 2015. On approximate reasoning capabilities of low-rank vector spaces. AAAI Spring Syposium on Knowledge Representation and Reasoning (KRR): Integrating Symbolic and Neural Approaches .
- Collobert, R.; Weston, J.; Bottou, L.; Karlen, M.; Kavukcuoglu, K.; and Kuksa, P. P. 2011. Natural Language Processing (Almost) from Scratch. Journal of Machine Learning Research 12:2493-2537.
- Defferrard, M.; Bresson, X.; and Vandergheynst, P. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In Proceedings of NIPS , 3837-3845.
- Dong, X.; Gabrilovich, E.; Heitz, G.; Horn, W.; Lao, N.; Murphy, K.; Strohmann, T.; Sun, S.; and Zhang, W. 2014. Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion. In Proceedings of KDD 2014 , 601-610.
- Duchi, J. C.; Hazan, E.; and Singer, Y . 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12:2121-2159.
- Duvenaud, D. K.; Maclaurin, D.; Aguilera-Iparraguirre, J.; Bombarell, R.; Hirzel, T.; Aspuru-Guzik, A.; and Adams, R. P. 2015. Convolutional Networks on Graphs for Learning Molecular Fingerprints. In Proceedings of NIPS 2015 , 22242232.
- Kalchbrenner, N.; Grefenstette, E.; and Blunsom, P. 2014. A Convolutional Neural Network for Modelling Sentences. In Proceedings of ACL 2014, Volume 1: Long Papers , 655-665.
- Kim, Y. 2014. Convolutional Neural Networks for Sentence Classification. In Proceedings of EMNLP 2014 , 1746-1751.
- Kipf, T. N., and Welling, M. 2016. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of ICLR 2016 .
- Krompaß, D.; Baier, S.; and Tresp, V. 2015. TypeConstrained Representation Learning in Knowledge Graphs. In Proceedings of ISWC 2015 , 640-655.
- Liu, Q.; Jiang, L.; Han, M.; Liu, Y.; and Qin, Z. 2016. Hierarchical random walk inference in knowledge graphs. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval , 445454. ACM.
- Liu, H.; Wu, Y.; and Yang, Y. 2017. Analogical Inference for Multi-Relational Embeddings. ArXiv e-prints .
- Mahdisoltani, F.; Biega, J.; and Suchanek, F. M. 2015. YAGO3: A Knowledge Base from Multilingual Wikipedias. In Proceedings of CIDR 2015 .
- Nickel, M.; Murphy, K.; Tresp, V.; and Gabrilovich, E. 2016. A review of relational machine learning for knowledge graphs. Proceedings of the IEEE 104(1):11-33.
- Nickel, M.; Rosasco, L.; and Poggio, T. A. 2016. Holographic Embeddings of Knowledge Graphs. In Proceedings of AAAI , 1955-1961.
- Niepert, M. 2016. Discriminative Gaifman Models. In Proceedings of NIPS 2016 , 3405-3413.
- Schlichtkrull, M.; Kipf, T. N.; Bloem, P.; Berg, R. v. d.; Titov, I.; and Welling, M. 2017. Modeling Relational Data with Graph Convolutional Networks. arXiv preprint arXiv:1703.06103 . · arXiv
- Shen, Y.; He, X.; Gao, J.; Deng, L.; and Mesnil, G. 2014. Learning Semantic Representations Using Convolutional Neural Networks for Web Search. In Proceedings of WWW 2014 , 373-374.
- Srivastava, N.; Hinton, G. E.; Krizhevsky, A.; Sutskever, I.; and Salakhutdinov, R. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research 15(1):1929-1958.
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; and Rabinovich, A. 2015. Going deeper with convolutions. In Proceedings of IEEE CVPR , 1-9.
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; and Wojna, Z. 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of IEEE CVPR , 2818-2826.
- Toutanova, K., and Chen, D. 2015. Observed Versus Latent Features for Knowledge Base and Text Inference. In Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality , 57-66.
- Toutanova, K.; Chen, D.; Pantel, P.; Poon, H.; Choudhury, P.; and Gamon, M. 2015. Representing Text for Joint Embedding of Text and Knowledge Bases. In Proceedings of EMNLP 2015 , volume 15, 1499-1509.
- Yang, B.; Yih, W.; He, X.; Gao, J.; and Deng, L. 2015. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In Proceedings of ICLR 2015 .
- Yih, W.; Toutanova, K.; Platt, J. C.; and Meek, C. 2011. Learning Discriminative Projections for Text Similarity Measures. In Proceedings of CoNLL 2011 , 247-256.
Cited by
Sorted by citations
Graph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880 · see citing works
Modeling Relational Data with Graph Convolutional Networks
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93417-4_38 · Cited by 5,570 · see citing works
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3070843 · Cited by 2,947 · see citing works
TuckER: Tensor Factorization for Knowledge Graph Completion
Balazevic, I., Allen, C., & Hospedales, T. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1522 · Cited by 696 · see citing works
Knowledge Enhanced Contextual Word Representations
Peters, M. E., Neumann, M., Logan, R., Schwartz, R., Joshi, V., Singh, S., & Smith, N. A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1005 · Cited by 661 · see citing works
Artificial intelligence in COVID-19 drug repurposing
Zhou, Y., Wang, F., Tang, J., Nussinov, R., & Cheng, F. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30192-8 · Cited by 636 · see citing works
Knowledge Graph Embedding for Link Prediction
Rossi, A., Barbosa, D., Firmani, D., Matinata, A., & Merialdo, P. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3424672 · Cited by 601 · see citing works
SimplE Embedding for Link Prediction in Knowledge Graphs
Kazemi, S. M., & Poole, D. (2018) · arXiv · doi:10.48550/arxiv.1802.04868 · Cited by 476 · see citing works
“In future, SimplE could be improved or may help improve relational learning in several ways including: 1- building ensembles of SimplE models as [18] do it for DistMult, 2- adding SimplE to the relation-level ensembles of [44], 3- explicitly modelling the analogical structures of relations as in [23], 4- using [8]’s 1…”
MethodCommonsense Knowledge Mining from Pretrained Models
Davison, J., Feldman, J., & Rush, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1109 · Cited by 264 · see citing works
A Survey of Data-driven and Knowledge-aware eXplainable AI
Li, X.-H., Cao, C. C., Shi, Y., Bai, W., Gao, H., Qiu, L., Wang, C., Gao, Y., Zhang, S., Xue, X., et al. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2983930 · Cited by 224 · see citing works
A Survey on Knowledge Graph Embeddings for Link Prediction
Wang, M., Qiu, L., & Wang, X. (2021) · Symmetry · doi:10.3390/sym13030485 · Cited by 212 · see citing works
CoLAKE: Contextualized Language and Knowledge Embedding
Sun, T., Shao, Y., Qiu, X., Guo, Q., Hu, Y., Huang, X., & Zhang, Z. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.327 · Cited by 185 · see citing works
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models
Zhang, Z., Liu, X., Zhang, Y., Su, Q., Sun, X., & He, B. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.25 · Cited by 52 · see citing works
Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones
Bai, Y., Ying, R., Ren, H., & Leskovec, J. (2021) · arXiv · doi:10.48550/arxiv.2110.14923 · Cited by 31 · see citing works
“We observe, using the groundtruth hypernym, hyponym and non-hierarchical relations in existing datasets (WN18RR, DDB14, GO21), that the Hierarchical-ness scores for hypernym, hyponym and non-hierarchical relations can be easily separated via decision boundaries.”
BackgroundMethodInfluentialSymmetry-Aware Knowledge Graph Compression for LLM Grounding via Symbolic Retrieval
Prakash, V., & Dontabhaktuni, J. (2026) · doi:10.2139/ssrn.6826298
- Authors
- Dettmers, T., Minervini, P., Stenetorp, P., & Riedel, S.
- Affiliations
- Università della Svizzera italiana (CH)
- University College London (GB)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-25
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2728059831
- Cited by
- 2,486
- References
- 7
- Citations by year
- 2026: 194 · 2025: 384 · 2024: 452 · 2023: 476 · 2022: 379 · 2021: 276 · 2020: 194 · 2019: 93 · 2018: 34 · 2017: 3 · 2016: 1
- FWCI
- 60.92
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Funders
- University College London
- Horizon 2020 Framework Programme
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- knowledge graph embedding, link prediction, convolutional neural networks, multilayer model, parameter efficiency, inverse relations, Freebase, DistMult
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.
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
