Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Haoyu, Cheng, Yuxuan, Fan, Wenqi, Chen, Yulong, Zhang, Yifan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.13254
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912648572960768
author Zhang, Haoyu
Cheng, Yuxuan
Fan, Wenqi
Chen, Yulong
Zhang, Yifan
author_facet Zhang, Haoyu
Cheng, Yuxuan
Fan, Wenqi
Chen, Yulong
Zhang, Yifan
contents Graph neural networks (GNNs) have achieved remarkable success in various domains, yet they often struggle with domain adaptation due to significant structural distribution shifts and insufficient exploration of transferable patterns. One of the main reasons behind this is that traditional approaches do not treat global and local patterns discriminatingly so that some local details in the graph may be violated after multi-layer GNN. Our key insight is that domain shifts can be better understood through spectral analysis, where low-frequency components often encode domain-invariant global patterns, and high-frequency components capture domain-specific local details. As such, we propose FracNet (\underline{\textbf{Fr}}equency \underline{\textbf{A}}ware \underline{\textbf{C}}ontrastive Graph \underline{\textbf{Net}}work) with two synergic modules to decompose the original graph into high-frequency and low-frequency components and perform frequency-aware domain adaption. Moreover, the blurring boundary problem of domain adaptation is improved by integrating with a contrastive learning framework. Besides the practical implication, we also provide rigorous theoretical proof to demonstrate the superiority of FracNet. Extensive experiments further demonstrate significant improvements over state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13254
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
Zhang, Haoyu
Cheng, Yuxuan
Fan, Wenqi
Chen, Yulong
Zhang, Yifan
Machine Learning
Graph neural networks (GNNs) have achieved remarkable success in various domains, yet they often struggle with domain adaptation due to significant structural distribution shifts and insufficient exploration of transferable patterns. One of the main reasons behind this is that traditional approaches do not treat global and local patterns discriminatingly so that some local details in the graph may be violated after multi-layer GNN. Our key insight is that domain shifts can be better understood through spectral analysis, where low-frequency components often encode domain-invariant global patterns, and high-frequency components capture domain-specific local details. As such, we propose FracNet (\underline{\textbf{Fr}}equency \underline{\textbf{A}}ware \underline{\textbf{C}}ontrastive Graph \underline{\textbf{Net}}work) with two synergic modules to decompose the original graph into high-frequency and low-frequency components and perform frequency-aware domain adaption. Moreover, the blurring boundary problem of domain adaptation is improved by integrating with a contrastive learning framework. Besides the practical implication, we also provide rigorous theoretical proof to demonstrate the superiority of FracNet. Extensive experiments further demonstrate significant improvements over state-of-the-art approaches.
title Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
topic Machine Learning
url https://arxiv.org/abs/2510.13254