Rethinking Propagation for Unsupervised Graph Domain Adaptation

域适应 适应(眼睛) 计算机科学 图形 理论计算机科学 人工智能 心理学 神经科学 分类器(UML)
作者
Meihan Liu,Zeyu Fang,Zhen Zhang,Ming Gu,Sheng Zhou,Xin Wang,Jiajun Bu
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence [Association for the Advancement of Artificial Intelligence (AAAI)]
卷期号:38 (12): 13963-13971 被引量:2
标识
DOI:10.1609/aaai.v38i12.29304
摘要

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled source graph to an unlabelled target graph in order to address the distribution shifts between graph domains. Previous works have primarily focused on aligning data from the source and target graph in the representation space learned by graph neural networks (GNNs). However, the inherent generalization capability of GNNs has been largely overlooked. Motivated by our empirical analysis, we reevaluate the role of GNNs in graph domain adaptation and uncover the pivotal role of the propagation process in GNNs for adapting to different graph domains. We provide a comprehensive theoretical analysis of UGDA and derive a generalization bound for multi-layer GNNs. By formulating GNN Lipschitz for k-layer GNNs, we show that the target risk bound can be tighter by removing propagation layers in source graph and stacking multiple propagation layers in target graph. Based on the empirical and theoretical analysis mentioned above, we propose a simple yet effective approach called A2GNN for graph domain adaptation. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of our proposed A2GNN framework.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
聪明的冬瓜完成签到,获得积分10
2秒前
fzx发布了新的文献求助10
4秒前
YMM发布了新的文献求助10
7秒前
NexusExplorer应助清新的寄翠采纳,获得10
8秒前
光亮若翠完成签到,获得积分10
13秒前
2024dsb完成签到 ,获得积分10
15秒前
15秒前
18秒前
19秒前
23秒前
25秒前
Teresa完成签到,获得积分20
25秒前
刘企盼完成签到,获得积分10
26秒前
顺利毕业应助super采纳,获得10
27秒前
明明明完成签到,获得积分10
29秒前
baobao发布了新的文献求助10
29秒前
FIN应助王欣采纳,获得10
30秒前
英姑应助义气安露采纳,获得10
30秒前
31秒前
科研通AI5应助LONG采纳,获得10
31秒前
星辰大海应助Salt采纳,获得10
32秒前
稳重奇异果应助ixueyi采纳,获得10
32秒前
聚合怪发布了新的文献求助10
36秒前
37秒前
慕青应助猫仔采纳,获得10
39秒前
Dr.Lee完成签到 ,获得积分10
39秒前
40秒前
聚合怪完成签到,获得积分20
41秒前
fzx关注了科研通微信公众号
42秒前
wangfeng007完成签到 ,获得积分10
43秒前
好大一个赣宝完成签到,获得积分10
44秒前
hailiangzheng完成签到,获得积分10
44秒前
45秒前
幸福幻灵发布了新的文献求助10
46秒前
46秒前
慕子默完成签到,获得积分10
47秒前
wade2016发布了新的文献求助10
47秒前
49秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
Production Logging: Theoretical and Interpretive Elements 3000
CRC Handbook of Chemistry and Physics 104th edition 1000
Izeltabart tapatansine - AdisInsight 600
Introduction to Comparative Public Administration Administrative Systems and Reforms in Europe, Third Edition 3rd edition 500
Distinct Aggregation Behaviors and Rheological Responses of Two Terminally Functionalized Polyisoprenes with Different Quadruple Hydrogen Bonding Motifs 450
THE STRUCTURES OF 'SHR' AND 'YOU' IN MANDARIN CHINESE 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3761824
求助须知:如何正确求助?哪些是违规求助? 3305615
关于积分的说明 10134845
捐赠科研通 3019634
什么是DOI,文献DOI怎么找? 1658255
邀请新用户注册赠送积分活动 792029
科研通“疑难数据库(出版商)”最低求助积分说明 754751