Covered Forest: Fine-grained generalization analysis of graph neural networks
This work addresses the generalization gap in MPNNs for researchers and practitioners in graph machine learning, though it appears incremental as it builds on existing theory.
The paper tackled the problem of understanding the generalization abilities of message-passing graph neural networks (MPNNs) by extending graph similarity theory to assess the influence of graph structure, aggregation, and loss functions, with empirical studies supporting theoretical insights.
The expressive power of message-passing graph neural networks (MPNNs) is reasonably well understood, primarily through combinatorial techniques from graph isomorphism testing. However, MPNNs' generalization abilities -- making meaningful predictions beyond the training set -- remain less explored. Current generalization analyses often overlook graph structure, limit the focus to specific aggregation functions, and assume the impractical, hard-to-optimize $0$-$1$ loss function. Here, we extend recent advances in graph similarity theory to assess the influence of graph structure, aggregation, and loss functions on MPNNs' generalization abilities. Our empirical study supports our theoretical insights, improving our understanding of MPNNs' generalization properties.