Learning Scalable Structural Representations for Link Prediction with Bloom Signatures

Abstract

Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to capture pairwise relations between target nodes, which proves to be crucial for link prediction. Recent works resort to learning more expressive edge-wise representations by enhancing vanilla GNNs with structural features such as labeling tricks and link prediction heuristics, but they suffer from high computational overhead and limited scalability. To tackle this issue, we propose to learn structural link representations by augmenting the message-passing framework of GNNs with Bloom signatures. Bloom signatures are hashing-based compact encodings of node neighborhoods, which can be efficiently merged to recover various types of edge-wise structural features. We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input. GNNs with Bloom signatures are provably more expressive than vanilla GNNs and also more scalable than existing edge-wise models. Experimental results on five standard link prediction benchmarks show that our proposed model achieves comparable or better performance than existing edge-wise GNN models while being 3-200 $\times$ faster and more memory-efficient for online inference.

References in corpus (8)

• Predicting Missing Links via Local Information
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
• Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
• Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
• SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
• Geodesic Graph Neural Network for Efficient Graph Representation Learning

Cited by in corpus (2)

• Understanding the Design Principles of Link Prediction in Directed Settings
• A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges