Saved in:
Bibliographic Details
Main Authors: Ayday, Nil, Yang, Lingchu, Ghoshdastidar, Debarghya
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.17569
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908897249329152
author Ayday, Nil
Yang, Lingchu
Ghoshdastidar, Debarghya
author_facet Ayday, Nil
Yang, Lingchu
Ghoshdastidar, Debarghya
contents Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models perform well in practice. In this work, we prove that attention-based architectures have structural benefits over graph convolutional networks in the context of node-level prediction tasks. Specifically, we study the neural network gaussian process limits of graph transformers (GAT, Graphormer, Specformer) with infinite width and infinite heads, and derive the node-level and edge-level kernels across the layers. Our results characterise how the node features and the graph structure propagate through the graph attention layers. As a specific example, we prove that graph transformers structurally preserve community information and maintain discriminative node representations even in deep layers, thereby preventing oversmoothing. We provide empirical evidence on synthetic and real-world graphs that validate our theoretical insights, such as integrating informative priors and positional encoding can improve performance of deep graph transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17569
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
Ayday, Nil
Yang, Lingchu
Ghoshdastidar, Debarghya
Machine Learning
Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models perform well in practice. In this work, we prove that attention-based architectures have structural benefits over graph convolutional networks in the context of node-level prediction tasks. Specifically, we study the neural network gaussian process limits of graph transformers (GAT, Graphormer, Specformer) with infinite width and infinite heads, and derive the node-level and edge-level kernels across the layers. Our results characterise how the node features and the graph structure propagate through the graph attention layers. As a specific example, we prove that graph transformers structurally preserve community information and maintain discriminative node representations even in deep layers, thereby preventing oversmoothing. We provide empirical evidence on synthetic and real-world graphs that validate our theoretical insights, such as integrating informative priors and positional encoding can improve performance of deep graph transformers.
title Gaussian Process Limit Reveals Structural Benefits of Graph Transformers
topic Machine Learning
url https://arxiv.org/abs/2603.17569