Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs

Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs

Xiaohan Xu, Peng Zhang, Yongquan He, Chengpeng Chao, Chaoyang Yan

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 2341-2347. https://doi.org/10.24963/ijcai.2022/325

Inductive link prediction for knowledge graph aims at predicting missing links between unseen entities, those not shown in training stage. Most previous works learn entity-specific embeddings of entities, which cannot handle unseen entities. Recent several methods utilize enclosing subgraph to obtain inductive ability. However, all these works only consider the enclosing part of subgraph without complete neighboring relations, which leads to the issue that partial neighboring relations are neglected, and sparse subgraphs are hard to be handled. To address that, we propose Subgraph Neighboring Relations Infomax, SNRI, which sufficiently exploits complete neighboring relations from two aspects: neighboring relational feature for node feature and neighboring relational path for sparse subgraph. To further model neighboring relations in a global way, we innovatively apply mutual information (MI) maximization for knowledge graph. Experiments show that SNRI outperforms existing state-of-art methods by a large margin on inductive link prediction task, and verify the effectiveness of exploring complete neighboring relations in a global way to characterize node features and reason on sparse subgraphs.
Keywords:
Data Mining: Knowledge Graphs and Knowledge Base Completion
Knowledge Representation and Reasoning: Learning and reasoning
Knowledge Representation and Reasoning: Reasoning about Knowledge and Belief
Machine Learning: Representation learning
Machine Learning: Self-supervised Learning