Learning Scalable Structural Representations for Link Prediction with Bloom Signatures

Tianyi Zhang, Haoteng Yin, Rongzhe Wei, Pan Li, Anshumali Shrivastava

Keywords: Graph Neural Networks, Link Prediction, Graph Representation Learning, Structural Features, Bloom Signatures, Hashing

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 single-node 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 complexity 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 encoding 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 which 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 standard link prediction benchmarks show that our proposed model achieves comparable or better performance than existing edge-wise GNN models while being 2-121 $\times$ faster and more memory-efficient for online inference.

Track: Graph Algorithms and Learning for the Web

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 2137