Rank and Align: Towards Effective Source-free Graph Domain Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Junyu, Xiao, Zhiping, Wang, Yifan, Luo, Xiao, Yuan, Jingyang, Ju, Wei, Liu, Langechuan, Zhang, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914920707129344
author Luo, Junyu
Xiao, Zhiping
Wang, Yifan
Luo, Xiao
Yuan, Jingyang
Ju, Wei
Liu, Langechuan
Zhang, Ming
author_facet Luo, Junyu
Xiao, Zhiping
Wang, Yifan
Luo, Xiao
Yuan, Jingyang
Ju, Wei
Liu, Langechuan
Zhang, Ming
contents Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12185
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rank and Align: Towards Effective Source-free Graph Domain Adaptation
Luo, Junyu
Xiao, Zhiping
Wang, Yifan
Luo, Xiao
Yuan, Jingyang
Ju, Wei
Liu, Langechuan
Zhang, Ming
Machine Learning
Artificial Intelligence
Information Retrieval
Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
title Rank and Align: Towards Effective Source-free Graph Domain Adaptation
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2408.12185