# Convolutional 2D Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/1707.01476 · HTML: https://mlsanity.com/paper/1707.01476/

## Key facts

- Cited by 730 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2017.

## Built on by (most cited first, 30 of 730)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey](https://mlsanity.com/paper/2302.10035/) (2023)
- [Fully Hyperbolic Neural Networks](https://mlsanity.com/paper/2105.14686/) (2021)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Knowledge Graph Reasoning with Relational Digraph](https://mlsanity.com/paper/2108.06040/) (2021)
- [SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models](https://mlsanity.com/paper/2203.02167/) (2022)
- [Towards Foundation Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2310.04562/) (2023)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Sequence-to-Sequence Knowledge Graph Completion and Question Answering](https://mlsanity.com/paper/2203.10321/) (2022)
- [NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs](https://mlsanity.com/paper/2106.12144/) (2021)
- [TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting](https://mlsanity.com/paper/2109.04101/) (2021)
- [FactKG: Fact Verification via Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2305.06590/) (2023)
- [Graph Coarsening with Neural Networks](https://mlsanity.com/paper/2102.01350/) (2021)
- [A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs](https://mlsanity.com/paper/2206.04798/) (2022)
- [Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/2103.03642/) (2021)
- [From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer](https://mlsanity.com/paper/2202.02113/) (2022)
- [Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure](https://mlsanity.com/paper/2211.10738/) (2022)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [Exploring Large Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2308.13916/) (2023)
- [Temporal Knowledge Graph Reasoning with Historical Contrastive Learning](https://mlsanity.com/paper/2211.10904/) (2022)
- [Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces](https://mlsanity.com/paper/2211.03536/) (2022)
- [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://mlsanity.com/paper/2302.02069/) (2023)
- [Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.00327/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones](https://mlsanity.com/paper/2110.14923/) (2021)
- [OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs](https://mlsanity.com/paper/2205.15117/) (2022)

## Abstract (arXiv)

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 most datasets.