提升消息传递网络的长程依赖捕捉能力，解决信息压缩问题。
Improving the Effective Receptive Field of Message-Passing Neural Networks
- 通过多尺度图粗化实现分层消息传递，增强跨距离信息交互。
- 在长程图基准上显著优于基线模型，保持高效计算开销。
- 适合处理具有长程依赖的复杂图数据任务，如分子建模与社交网络分析。
消息传递神经网络（MPNN）已成为处理图结构数据的核心工具，但其性能常受过压缩现象制约——长程依赖难以有效捕捉和表达。这一问题与卷积神经网络中有效感受野（ERF）理论与实际使用间的差距类似。本文首次理论揭示了MPNN中有效感受野受限的现象，并受卷积网络中增强有效感受野方法的启发，提出交错多尺度消息传递网络（IM-MPNN）。该架构通过图的层次粗化，支持跨多尺度表示的消息传递，实现长程交互而无需增加网络深度或参数量。在长程图基准（LRGB）等标准测试集上的大量实验表明，所提方法在捕捉长程依赖方面有显著提升，同时保持良好的计算效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。