Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning

2026-08-27

AI Summary

本文提出RTA框架，通过标签感知检索和传播替代结构消息传递，解决GNN计算昂贵及对不完美图结构敏感的问题。

Abstract

Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks, yet it remains unclear why neighborhood aggregation reliably outperforms node-wise multilayer perceptrons (MLPs). Despite its empirical success, this paradigm can be computationally expensive and sensitive to imperfect graph structures. In this work, we present a retrieval-augmented view of GNNs: each layer makes predictions by applying an MLP to a node representation together with a permutation-invariant summary of retrieved graph context. Motivated by this perspective, we propose RTA, a simple MLP-based framework that replaces structural message passing with label-aware retrieval and propagation. We provide theoretical insights that (i) connect retrieval-based aggregation to softmax-attention message passing, and (ii) establish the robustness of retrieved-context supervision to mis-retrieved outliers. Experiments on multiple text-attributed graph benchmarks show that RTA matches or even outperforms strong GNN and graph LLM baselines while improving efficiency and robustness across diverse scenarios.

Problem

• Graph Neural Networks
• Message Passing
• Node-wise MLPs
• Retrieval
• Text-Attributed Graphs

Innovation

• retrieval-augmented view
• label-aware retrieval
• softmax-attention message passing
• robustness to mis-retrieved outliers