Saved in:
Bibliographic Details
Main Authors: Luo, Haitong, Wang, Suhang, Zhang, Weiyao, Meng, Ruiqi, Meng, Xuying, Zhang, Yujun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.11328
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911367442726912
author Luo, Haitong
Wang, Suhang
Zhang, Weiyao
Meng, Ruiqi
Meng, Xuying
Zhang, Yujun
author_facet Luo, Haitong
Wang, Suhang
Zhang, Weiyao
Meng, Ruiqi
Meng, Xuying
Zhang, Yujun
contents Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, current methods typically rely on single-filter backbones (e.g., low-pass), whereas real-world graphs exhibit inherent spectral diversity. Our theoretical \textit{Spectral Specificity} principle reveals that effective knowledge transfer requires alignment between pre-trained spectral filters and the intrinsic spectrum of downstream graphs. This identifies two fundamental limitations: (1) Knowledge Bottleneck: single-filter models suffer from irreversible information loss by suppressing signals from other frequency bands (e.g., high-frequency); (2) Utilization Bottleneck: spectral mismatches between pre-trained filters and downstream spectra lead to significant underutilization of pre-trained knowledge. To bridge this gap, we propose HS-GPPT. We utilize a hybrid spectral backbone to construct an abundant knowledge basis. Crucially, we introduce Spectral-Aligned Prompt Tuning to actively align the downstream graph's spectrum with diverse pre-trained filters, facilitating comprehensive knowledge utilization across both homophily and heterophily. Extensive experiments validate the effectiveness under both transductive and inductive learning settings.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11328
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily
Luo, Haitong
Wang, Suhang
Zhang, Weiyao
Meng, Ruiqi
Meng, Xuying
Zhang, Yujun
Machine Learning
Computation and Language
Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, current methods typically rely on single-filter backbones (e.g., low-pass), whereas real-world graphs exhibit inherent spectral diversity. Our theoretical \textit{Spectral Specificity} principle reveals that effective knowledge transfer requires alignment between pre-trained spectral filters and the intrinsic spectrum of downstream graphs. This identifies two fundamental limitations: (1) Knowledge Bottleneck: single-filter models suffer from irreversible information loss by suppressing signals from other frequency bands (e.g., high-frequency); (2) Utilization Bottleneck: spectral mismatches between pre-trained filters and downstream spectra lead to significant underutilization of pre-trained knowledge. To bridge this gap, we propose HS-GPPT. We utilize a hybrid spectral backbone to construct an abundant knowledge basis. Crucially, we introduce Spectral-Aligned Prompt Tuning to actively align the downstream graph's spectrum with diverse pre-trained filters, facilitating comprehensive knowledge utilization across both homophily and heterophily. Extensive experiments validate the effectiveness under both transductive and inductive learning settings.
title Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2508.11328