Towards Dynamic Message Passing on Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Junshu, Yang, Chenxue, Ji, Xiangyang, Huang, Qingming, Wang, Shuhui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929609216360448
author Sun, Junshu
Yang, Chenxue
Ji, Xiangyang
Huang, Qingming
Wang, Shuhui
author_facet Sun, Junshu
Yang, Chenxue
Ji, Xiangyang
Huang, Qingming
Wang, Shuhui
contents Message passing plays a vital role in graph neural networks (GNNs) for effective feature learning. However, the over-reliance on input topology diminishes the efficacy of message passing and restricts the ability of GNNs. Despite efforts to mitigate the reliance, existing study encounters message-passing bottlenecks or high computational expense problems, which invokes the demands for flexible message passing with low complexity. In this paper, we propose a novel dynamic message-passing mechanism for GNNs. It projects graph nodes and learnable pseudo nodes into a common space with measurable spatial relations between them. With nodes moving in the space, their evolving relations facilitate flexible pathway construction for a dynamic message-passing process. Associating pseudo nodes to input graphs with their measured relations, graph nodes can communicate with each other intermediately through pseudo nodes under linear complexity. We further develop a GNN model named $\mathtt{\mathbf{N^2}}$ based on our dynamic message-passing mechanism. $\mathtt{\mathbf{N^2}}$ employs a single recurrent layer to recursively generate the displacements of nodes and construct optimal dynamic pathways. Evaluation on eighteen benchmarks demonstrates the superior performance of $\mathtt{\mathbf{N^2}}$ over popular GNNs. $\mathtt{\mathbf{N^2}}$ successfully scales to large-scale benchmarks and requires significantly fewer parameters for graph classification with the shared recurrent layer.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23686
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Dynamic Message Passing on Graphs
Sun, Junshu
Yang, Chenxue
Ji, Xiangyang
Huang, Qingming
Wang, Shuhui
Machine Learning
Message passing plays a vital role in graph neural networks (GNNs) for effective feature learning. However, the over-reliance on input topology diminishes the efficacy of message passing and restricts the ability of GNNs. Despite efforts to mitigate the reliance, existing study encounters message-passing bottlenecks or high computational expense problems, which invokes the demands for flexible message passing with low complexity. In this paper, we propose a novel dynamic message-passing mechanism for GNNs. It projects graph nodes and learnable pseudo nodes into a common space with measurable spatial relations between them. With nodes moving in the space, their evolving relations facilitate flexible pathway construction for a dynamic message-passing process. Associating pseudo nodes to input graphs with their measured relations, graph nodes can communicate with each other intermediately through pseudo nodes under linear complexity. We further develop a GNN model named $\mathtt{\mathbf{N^2}}$ based on our dynamic message-passing mechanism. $\mathtt{\mathbf{N^2}}$ employs a single recurrent layer to recursively generate the displacements of nodes and construct optimal dynamic pathways. Evaluation on eighteen benchmarks demonstrates the superior performance of $\mathtt{\mathbf{N^2}}$ over popular GNNs. $\mathtt{\mathbf{N^2}}$ successfully scales to large-scale benchmarks and requires significantly fewer parameters for graph classification with the shared recurrent layer.
title Towards Dynamic Message Passing on Graphs
topic Machine Learning
url https://arxiv.org/abs/2410.23686