Simplifying Subgraph Representation Learning for Scalable Link Prediction
This addresses scalability issues for researchers and practitioners working with large-scale graphs in link prediction tasks, representing an incremental improvement over existing SGRL methods.
The paper tackled the computational expense and lack of scalability in subgraph representation learning (SGRL) for link prediction by proposing Scalable Simplified SGRL (S3GRL), which simplifies operations to achieve multi-fold speedups in training and inference while maintaining or improving performance.
Link prediction on graphs is a fundamental problem. Subgraph representation learning approaches (SGRLs), by transforming link prediction to graph classification on the subgraphs around the links, have achieved state-of-the-art performance in link prediction. However, SGRLs are computationally expensive, and not scalable to large-scale graphs due to expensive subgraph-level operations. To unlock the scalability of SGRLs, we propose a new class of SGRLs, that we call Scalable Simplified SGRL (S3GRL). Aimed at faster training and inference, S3GRL simplifies the message passing and aggregation operations in each link's subgraph. S3GRL, as a scalability framework, accommodates various subgraph sampling strategies and diffusion operators to emulate computationally-expensive SGRLs. We propose multiple instances of S3GRL and empirically study them on small to large-scale graphs. Our extensive experiments demonstrate that the proposed S3GRL models scale up SGRLs without significant performance compromise (even with considerable gains in some cases), while offering substantially lower computational footprints (e.g., multi-fold inference and training speedup).