GCAL: Adapting Graph Models to Evolving Domain Shifts

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qiao, Ziyue, Cai, Qianyi, Dong, Hao, Gu, Jiawei, Wang, Pengyang, Xiao, Meng, Luo, Xiao, Xiong, Hui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915298789031936
author Qiao, Ziyue
Cai, Qianyi
Dong, Hao
Gu, Jiawei
Wang, Pengyang
Xiao, Meng
Luo, Xiao
Xiong, Hui
author_facet Qiao, Ziyue
Cai, Qianyi
Dong, Hao
Gu, Jiawei
Wang, Pengyang
Xiao, Meng
Luo, Xiao
Xiong, Hui
contents This paper addresses the challenge of graph domain adaptation on evolving, multiple out-of-distribution (OOD) graphs. Conventional graph domain adaptation methods are confined to single-step adaptation, making them ineffective in handling continuous domain shifts and prone to catastrophic forgetting. This paper introduces the Graph Continual Adaptive Learning (GCAL) method, designed to enhance model sustainability and adaptability across various graph domains. GCAL employs a bilevel optimization strategy. The "adapt" phase uses an information maximization approach to fine-tune the model with new graph domains while re-adapting past memories to mitigate forgetting. Concurrently, the "generate memory" phase, guided by a theoretical lower bound derived from information bottleneck theory, involves a variational memory graph generation module to condense original graphs into memories. Extensive experimental evaluations demonstrate that GCAL substantially outperforms existing methods in terms of adaptability and knowledge retention.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GCAL: Adapting Graph Models to Evolving Domain Shifts
Qiao, Ziyue
Cai, Qianyi
Dong, Hao
Gu, Jiawei
Wang, Pengyang
Xiao, Meng
Luo, Xiao
Xiong, Hui
Machine Learning
Artificial Intelligence
This paper addresses the challenge of graph domain adaptation on evolving, multiple out-of-distribution (OOD) graphs. Conventional graph domain adaptation methods are confined to single-step adaptation, making them ineffective in handling continuous domain shifts and prone to catastrophic forgetting. This paper introduces the Graph Continual Adaptive Learning (GCAL) method, designed to enhance model sustainability and adaptability across various graph domains. GCAL employs a bilevel optimization strategy. The "adapt" phase uses an information maximization approach to fine-tune the model with new graph domains while re-adapting past memories to mitigate forgetting. Concurrently, the "generate memory" phase, guided by a theoretical lower bound derived from information bottleneck theory, involves a variational memory graph generation module to condense original graphs into memories. Extensive experimental evaluations demonstrate that GCAL substantially outperforms existing methods in terms of adaptability and knowledge retention.
title GCAL: Adapting Graph Models to Evolving Domain Shifts
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.16860