Improving the Effective Receptive Field of Message-Passing Neural Networks
This addresses a key bottleneck in graph neural networks for tasks requiring long-range interactions, representing an incremental advance over existing MPNN methods.
The paper tackles the limited effective receptive field problem in Message-Passing Neural Networks (MPNNs), which hinders long-range dependency capture, and proposes an Interleaved Multiscale MPNN architecture that achieves substantial improvements on benchmarks like LRGB while maintaining computational efficiency.
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.