paper-with-me

홈 › Papers

Breaking the Limits of Message Passing Graph Neural Networks

2021-06-08 · Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère, Pascal Vasseur, Sébastien Adam, Paul Honeine

Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL). In this paper, we show that if the graph convolution supports are designed in spectral-domain by a non-linear custom function of eigenvalues and masked with an arbitrary large receptive field, the MPNN is theoretically more powerful than the 1-WL test and experimentally as powerful as a 3-WL existing models, while remaining spatially localized. Moreover, by designing custom filter functions, outputs can have various frequency components that allow the convolution process to learn different relationships between a given input graph signal and its associated properties. So far, the best 3-WL equivalent graph neural networks have a computational complexity in $\mathcal{O}(n^3)$ with memory usage in $\mathcal{O}(n^2)$, consider non-local update mechanism and do not provide the spectral richness of output profile. The proposed method overcomes all these aforementioned problems and reaches state-of-the-art results in many downstream tasks.

📄 PDF Abstract BibTeX arXiv:2106.04319

Code (2)

balcilar/gnn-matlang 공식 구현 pytorch
nur-ag/gnn-matlang pytorch

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
MPNN There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we…

Similar Papers 제목 키워드 기반

Shortest Path Networks for Graph Property Prediction

2022-06-02 · Ralph Abboud, Radoslav Dimitrov, İsmail İlkan Ceylan

Most graph neural network models rely on a particular message passing paradigm, where the idea is to iteratively propagate node representations of a graph to each node in the direct neighborhood. While very prominent, th…

Graph ClassificationGraph Neural NetworkGraph Property PredictionPrediction+1

Generalization and Representational Limits of Graph Neural Networks

2020-02-14 · ICML 2020 1 · Vikas K. Garg, Stefanie Jegelka, Tommi Jaakkola

We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the s…

Generalization Bounds

Multigraph Message Passing with Bi-Directional Multi-Edge Aggregations

2024-11-29 · H. Çağrı Bilgi, Lydia Y. Chen, Kubilay Atasu

Graph Neural Networks (GNNs) have seen significant advances in recent years, yet their application to multigraphs, where parallel edges exist between the same pair of nodes, remains under-explored. Standard GNNs, designe…

Graph Learning

LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence

2023-02-02 · Zhihao Shi, Xize Liang, Jie Wang

The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e…

On the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition

2025-07-09 · Lucas Tesan, Mikel M. Iparraguirre, David Gonzalez, Pedro Martins 외 arxiv

This paper proposes sharp lower bounds for the number of message passing iterations required in graph neural networks (GNNs) when solving partial differential equations (PDE). This significantly reduces the need for exha…