SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
This work is significant for researchers and practitioners using GNNs in real-world applications where explicit graph structures are often unavailable, providing a more robust method for structure inference.
This paper addresses the problem of missing graph structures for Graph Neural Networks (GNNs) by proposing SLAPS, a method that uses self-supervision to infer task-specific latent structures. SLAPS scales to large graphs with hundreds of thousands of nodes and outperforms existing models on established benchmarks.
Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this problem is to infer a task-specific latent structure and then apply a GNN to the inferred graph. Unfortunately, the space of possible graph structures grows super-exponentially with the number of nodes and so the task-specific supervision may be insufficient for learning both the structure and the GNN parameters. In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision. A comprehensive experimental study demonstrates that SLAPS scales to large graphs with hundreds of thousands of nodes and outperforms several models that have been proposed to learn a task-specific graph structure on established benchmarks.