Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

arXiv:2408.07088v1 Announce Type: new
Abstract: Inductive relation prediction (IRP) — where entities can be different during training and inference — has shown great power for completing evolving knowledge graphs. Existing works mainly focus on using graph neural networks (GNNs) to learn the representation of the subgraph induced from the target link, which can be seen as an implicit rule-mining process to measure the plausibility of the target link. However, these methods cannot differentiate the target link and other links during message passing, hence the final subgraph representation will contain irrelevant rule information to the target link, which reduces the reasoning performance and severely hinders the applications for real-world scenarios. To tackle this problem, we propose a novel textit{single-source edge-wise} GNN model to learn the textbf{R}ule-inductextbf{E}d textbf{S}ubgraph representextbf{T}ations (textbf{REST}), which encodes relevant rules and eliminates irrelevant rules within the subgraph. Specifically, we propose a textit{single-source} initialization approach to initialize edge features only for the target link, which guarantees the relevance of mined rules and target link. Then we propose several RNN-based functions for textit{edge-wise} message passing to model the sequential property of mined rules. REST is a simple and effective approach with theoretical support to learn the textit{rule-induced subgraph representation}. Moreover, REST does not need node labeling, which significantly accelerates the subgraph preprocessing time by up to textbf{11.66$times$}. Experiments on inductive relation prediction benchmarks demonstrate the effectiveness of our REST. Our code is available at https://github.com/smart-lty/REST.



Source link
lol