Improving the Effective Receptive Field of Message-Passing Neural Networks

TL;DR

This paper identifies the limited effective receptive field in message-passing neural networks and proposes a multiscale architecture to enhance long-range dependency modeling, demonstrating significant improvements on benchmark datasets.

Contribution

It introduces a novel multiscale message-passing architecture inspired by CNN ERF augmentation techniques to address ERF limitations in MPNNs.

Findings

Substantial performance gains on Long-Range Graph Benchmark (LRGB).

Enhanced ability to capture long-range dependencies.

Maintains computational efficiency with multiscale approach.

Abstract

Message-Passing Neural Networks (MPNNs) have become a cornerstone for processing and analyzing graph-structured data. However, their effectiveness is often hindered by phenomena such as over-squashing, where long-range dependencies or interactions are inadequately captured and expressed in the MPNN output. This limitation mirrors the challenges of the Effective Receptive Field (ERF) in Convolutional Neural Networks (CNNs), where the theoretical receptive field is underutilized in practice. In this work, we show and theoretically explain the limited ERF problem in MPNNs. Furthermore, inspired by recent advances in ERF augmentation for CNNs, we propose an Interleaved Multiscale Message-Passing Neural Networks (IM-MPNN) architecture to address these problems in MPNNs. Our method incorporates a hierarchical coarsening of the graph, enabling message-passing across multiscale representations and facilitating long-range interactions without excessive depth or parameterization. Through extensive evaluations on benchmarks such as the Long-Range Graph Benchmark (LRGB), we demonstrate substantial improvements over baseline MPNNs in capturing long-range dependencies while maintaining computational efficiency.