Rethinking Propagation for Unsupervised Graph Domain Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913227735040000 |
|---|---|
| author | Liu, Meihan Fang, Zeyu Zhang, Zhen Gu, Ming Zhou, Sheng Wang, Xin Bu, Jiajun |
| author_facet | Liu, Meihan Fang, Zeyu Zhang, Zhen Gu, Ming Zhou, Sheng Wang, Xin Bu, Jiajun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05660 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Propagation for Unsupervised Graph Domain Adaptation Liu, Meihan Fang, Zeyu Zhang, Zhen Gu, Ming Zhou, Sheng Wang, Xin Bu, Jiajun Machine Learning Artificial Intelligence 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. |
| title | Rethinking Propagation for Unsupervised Graph Domain Adaptation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.05660 |