Improving the Effective Receptive Field of Message-Passing Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Finder, Shahaf E., Weber, Ron Shapira, Eliasof, Moshe, Freifeld, Oren, Treister, Eran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916766102323200
author Finder, Shahaf E.
Weber, Ron Shapira
Eliasof, Moshe
Freifeld, Oren
Treister, Eran
author_facet Finder, Shahaf E.
Weber, Ron Shapira
Eliasof, Moshe
Freifeld, Oren
Treister, Eran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving the Effective Receptive Field of Message-Passing Neural Networks
Finder, Shahaf E.
Weber, Ron Shapira
Eliasof, Moshe
Freifeld, Oren
Treister, Eran
Machine Learning
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.
title Improving the Effective Receptive Field of Message-Passing Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2505.23185