Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection

TL;DR

This paper introduces PS2, a personalized subgraph selector for GNN-based link prediction, which automatically identifies optimal subgraphs for each edge, improving prediction accuracy across various models and datasets.

Contribution

The paper proposes a novel bi-level optimization framework, PS2, for personalized subgraph selection in GNN link prediction, addressing the limitations of fixed subgraphs and enabling inductive, edge-specific subgraph identification.

Findings

PS2 improves link prediction accuracy across multiple GNN models.

Personalized subgraph selection outperforms fixed subgraph approaches.

The method is effective on diverse datasets and benchmarks.

Abstract

Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply GNNs to encode edge representations by leveraging the neighborhood structure induced by the fixed subgraph. The prominence of GNNLP methods significantly relies on the adhoc subgraph. Since node connectivity in real-world graphs is complex, one shared subgraph is limited for all edges. Thus, the choices of subgraphs should be personalized to different edges. However, performing personalized subgraph selection is nontrivial since the potential selection space grows exponentially to the scale of edges. Besides, the inference edges are not available during training in link prediction scenarios, so the selection process needs to be inductive. To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP. PS2 is instantiated as a bi-level optimization problem that can be efficiently solved differently. Coupling GNNLP models with PS2, we suggest a brand-new angle towards GNNLP training: by first identifying the optimal subgraphs for edges; and then focusing on training the inference model by using the sampled subgraphs. Comprehensive experiments endorse the effectiveness of our proposed method across various GNNLP backbones (GCN, GraphSage, NGCF, LightGCN, and SEAL) and diverse benchmarks (Planetoid, OGB, and Recommendation datasets). Our code is publicly available at \url{https://github.com/qiaoyu-tan/PS2}