|国家预印本平台
首页|SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation

SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation

SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation

来源:Arxiv_logoArxiv
英文摘要

Domain Adaptation (DA) aims to transfer knowledge from a labeled source domain to an unlabeled or sparsely labeled target domain under domain shifts. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. To tackle this tradeoff, we propose a generalized graph SPectral Alignment framework, SPA++. Its core is briefly condensed as follows: (1)-by casting the DA problem to graph primitives, it composes a coarse graph alignment mechanism with a novel spectral regularizer toward aligning the domain graphs in eigenspaces; (2)-we further develop a fine-grained neighbor-aware propagation mechanism for enhanced discriminability in the target domain; (3)-by incorporating data augmentation and consistency regularization, SPA++ can adapt to complex scenarios including most DA settings and even challenging distribution scenarios. Furthermore, we also provide theoretical analysis to support our method, including the generalization bound of graph-based DA and the role of spectral alignment and smoothing consistency. Extensive experiments on benchmark datasets demonstrate that SPA++ consistently outperforms existing cutting-edge methods, achieving superior robustness and adaptability across various challenging adaptation scenarios.

Zhiqing Xiao、Haobo Wang、Xu Lu、Wentao Ye、Gang Chen、Junbo Zhao

计算技术、计算机技术

Zhiqing Xiao,Haobo Wang,Xu Lu,Wentao Ye,Gang Chen,Junbo Zhao.SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation[EB/OL].(2025-08-08)[2025-08-18].https://arxiv.org/abs/2508.05182.点此复制

评论