SOURCE-LINKED INTELLIGENCE

Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

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-b

Read original source ↗ Open in workspace

recordType

paper

region

Global