Pith. sign in

REVIEW 1 cited by

Technical Report: The Graph Spectral Token -- Enhancing Graph Transformers with Spectral Information

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.05604 v1 pith:ED677T2A submitted 2024-04-08 cs.LG

Technical Report: The Graph Spectral Token -- Enhancing Graph Transformers with Spectral Information

classification cs.LG
keywords graphspectralinformationtokentransformersapproachbenchmarkdatasets
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Graph Transformers have emerged as a powerful alternative to Message-Passing Graph Neural Networks (MP-GNNs) to address limitations such as over-squashing of information exchange. However, incorporating graph inductive bias into transformer architectures remains a significant challenge. In this report, we propose the Graph Spectral Token, a novel approach to directly encode graph spectral information, which captures the global structure of the graph, into the transformer architecture. By parameterizing the auxiliary [CLS] token and leaving other tokens representing graph nodes, our method seamlessly integrates spectral information into the learning process. We benchmark the effectiveness of our approach by enhancing two existing graph transformers, GraphTrans and SubFormer. The improved GraphTrans, dubbed GraphTrans-Spec, achieves over 10% improvements on large graph benchmark datasets while maintaining efficiency comparable to MP-GNNs. SubFormer-Spec demonstrates strong performance across various datasets.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

    cs.LG 2026-07 conditional novelty 6.5

    Under a denoising objective, linear attention is suboptimal; Graph Convolutional Attention matches idealized spectral attention on SBMs and improves graph denoising and diffusion in proportion to spectral diversity.