Models and Benchmarks for Representation Learning of Partially Observed Subgraphs
This addresses the challenge of suboptimal representations in graph-based tasks under partial observation, but it is incremental as it generalizes existing InfoMax models.
The paper tackles the problem of learning representations for partially observed subgraphs in graphs, proposing the Partial Subgraph InfoMax (PSI) framework and a two-stage model with k-hop PSI, which outperforms baselines on three real-world datasets.
Subgraphs are rich substructures in graphs, and their nodes and edges can be partially observed in real-world tasks. Under partial observation, existing node- or subgraph-level message-passing produces suboptimal representations. In this paper, we formulate a novel task of learning representations of partially observed subgraphs. To solve this problem, we propose Partial Subgraph InfoMax (PSI) framework and generalize existing InfoMax models, including DGI, InfoGraph, MVGRL, and GraphCL, into our framework. These models maximize the mutual information between the partial subgraph's summary and various substructures from nodes to full subgraphs. In addition, we suggest a novel two-stage model with $k$-hop PSI, which reconstructs the representation of the full subgraph and improves its expressiveness from different local-global structures. Under training and evaluation protocols designed for this problem, we conduct experiments on three real-world datasets and demonstrate that PSI models outperform baselines.