ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Chaohao, Song, Zhenjie, Kuruoglu, Ercan Engin, Zhao, Kangfei, Liu, Yang, Zhao, Deli, Cheng, Hong, Rong, Yu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912768924319744
author Yuan, Chaohao
Song, Zhenjie
Kuruoglu, Ercan Engin
Zhao, Kangfei
Liu, Yang
Zhao, Deli
Cheng, Hong
Rong, Yu
author_facet Yuan, Chaohao
Song, Zhenjie
Kuruoglu, Ercan Engin
Zhao, Kangfei
Liu, Yang
Zhao, Deli
Cheng, Hong
Rong, Yu
contents Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was initially introduced, eliminating the necessity for using deep GNNs. However, through empirical and theoretical analysis, we verify that the introduced global attention exhibits severe over-smoothing, causing node representations to become indistinguishable due to its inherent low-pass filtering. This effect is even stronger than that observed in GNNs. To mitigate this, we propose PageRank Transformer (ParaFormer), which features a PageRank-enhanced attention module designed to mimic the behavior of deep Transformers. We theoretically and empirically demonstrate that ParaFormer mitigates over-smoothing by functioning as an adaptive-pass filter. Experiments show that ParaFormer achieves consistent performance improvements across both node classification and graph classification tasks on 11 datasets ranging from thousands to millions of nodes, validating its efficacy. The supplementary material, including code and appendix, can be found in https://github.com/chaohaoyuan/ParaFormer.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14619
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
Yuan, Chaohao
Song, Zhenjie
Kuruoglu, Ercan Engin
Zhao, Kangfei
Liu, Yang
Zhao, Deli
Cheng, Hong
Rong, Yu
Machine Learning
Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was initially introduced, eliminating the necessity for using deep GNNs. However, through empirical and theoretical analysis, we verify that the introduced global attention exhibits severe over-smoothing, causing node representations to become indistinguishable due to its inherent low-pass filtering. This effect is even stronger than that observed in GNNs. To mitigate this, we propose PageRank Transformer (ParaFormer), which features a PageRank-enhanced attention module designed to mimic the behavior of deep Transformers. We theoretically and empirically demonstrate that ParaFormer mitigates over-smoothing by functioning as an adaptive-pass filter. Experiments show that ParaFormer achieves consistent performance improvements across both node classification and graph classification tasks on 11 datasets ranging from thousands to millions of nodes, validating its efficacy. The supplementary material, including code and appendix, can be found in https://github.com/chaohaoyuan/ParaFormer.
title ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
topic Machine Learning
url https://arxiv.org/abs/2512.14619