SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

Bahare Fatemi, Seyed Mehran Kazemi, Layla El Asri

Keywords: Graph Neural Networks, Graph Representation Learning, Graph Structure Learning, Self-supervision

Abstract: 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 the 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 available node labels 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. This approach consists of training a denoising autoencoder GNN in parallel with the task-specific GNN. The autoencoder is trained to reconstruct the initial node features given noisy node features as well as a structure provided by a learnable graph generator. We explore the design space of SLAPS by comparing different graph generation and symmetrization approaches. 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.

One-sentence Summary: Self-Supervision Improves Structure Learning for Graph Neural Networks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=wDNTXOqJsq