# How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View

arXiv: https://arxiv.org/abs/2109.11800 · HTML: https://mlsanity.com/paper/2109.11800/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 24 Sep 2021.

## Builds on (most cited first, 19 of 19)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks](https://mlsanity.com/paper/2009.11848/) (2020)
- [On the Inductive Bias of Neural Tangent Kernels](https://mlsanity.com/paper/1905.12173/) (2019)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion](https://mlsanity.com/paper/1811.04441/) (2018)
- [Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs](https://mlsanity.com/paper/1906.01195/) (2019)
- [A Re-evaluation of Knowledge Graph Completion Methods](https://mlsanity.com/paper/1911.03903/) (2019)
- [PairRE: Knowledge Graph Embeddings via Paired Relation Vectors](https://mlsanity.com/paper/2011.03798/) (2020)
- [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://mlsanity.com/paper/1911.02707/) (2019)
- [InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions](https://mlsanity.com/paper/1911.00219/) (2019)
- [A Survey on Graph Neural Networks for Knowledge Graph Completion](https://mlsanity.com/paper/2007.12374/) (2020)
- [Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis](https://mlsanity.com/paper/2104.04676/) (2021)

## Built on by (most cited first, 17 of 17)

- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [Toward Degree Bias in Embedding-Based Knowledge Graph Completion](https://mlsanity.com/paper/2302.05044/) (2023)
- [ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective](https://mlsanity.com/paper/2207.09980/) (2022)
- [On the Evolution of Knowledge Graphs: A Survey and Perspective](https://mlsanity.com/paper/2310.04835/) (2023)
- [Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph](https://mlsanity.com/paper/2302.05640/) (2023)
- [Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion](https://mlsanity.com/paper/2406.18166/) (2024)
- [Exploring & Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2306.17034/) (2023)
- [Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning](https://mlsanity.com/paper/2509.01166/) (2025)
- [Analogical Inference Enhanced Knowledge Graph Embedding](https://mlsanity.com/paper/2301.00982/) (2023)
- [Knowledge Graph Reasoning with Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2405.13640/) (2024)
- [VEM2L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2207.01528/) (2022)
- [NeuralKG-ind: A Python Library for Inductive Knowledge Graph Representation Learning](https://mlsanity.com/paper/2304.14678/) (2023)
- [Bridging the Semantic-Numerical Gap: A Numerical Reasoning Method of Cross-modal Knowledge Graph for Material Property Prediction](https://mlsanity.com/paper/2312.09744/) (2023)
- [Node-based Knowledge Graph Contrastive Learning for Medical Relationship Prediction](https://mlsanity.com/paper/2310.10138/) (2023)
- [SF-GNN: Self Filter for Message Lossless Propagation in Deep Graph Neural Network](https://mlsanity.com/paper/2407.02762/) (2024)
- [Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey](https://mlsanity.com/paper/2607.09666/) (2026)
- [More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning](https://mlsanity.com/paper/2608.29139/) (2026)

## Abstract (arXiv)

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://github.com/renli1024/SE-GNN.