How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View
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.
Code (1)
Tasks
Graph EmbeddingGraph Neural NetworkKnowledge Graph CompletionKnowledge Graph EmbeddingLink PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
Many practical graph problems, such as knowledge graph construction and drug-drug interaction prediction, require to handle multi-relational graphs. However, handling real-world multi-relational graphs with Graph Neural …
graph constructionKnowledge Graph CompletionLink PredictionMeta-Learning+1Inference over Unseen Entities, Relations and Literals on Knowledge Graphs
In recent years, knowledge graph embedding models have been successfully applied in the transductive setting to tackle various challenging tasks including link prediction, and query answering. Yet, the transductive setti…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink PredictionOpen World Learning Graph Convolution for Latency Estimation in Routing Networks
Accurate routing network status estimation is a key component in Software Defined Networking. However, existing deep-learning-based methods for modeling network routing are not able to extrapolate towards unseen feature …
Deep LearningAn Open-World Extension to Knowledge Graph Completion Models
We present a novel extension to embedding-based knowledge graph completion models which enables them to perform open-world link prediction, i.e. to predict facts for entities unseen in training based on their textual des…
Knowledge Graph CompletionLink PredictionPredictionWord EmbeddingsFirst Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
Real-world machine learning applications often involve deploying neural networks to domains that are not seen in the training time. Hence, we need to understand the extrapolation of nonlinear models -- under what conditi…