Timezone: »

Spotlight Poster
Subspace Identification for Multi-Source Domain Adaptation
Zijian Li · Ruichu Cai · Guangyi Chen · Boyang Sun · Zhifeng Hao · Kun Zhang

Tue Dec 12 08:45 AM -- 10:45 AM (PST) @ Great Hall & Hall B1+B2 #1708

Multi-source domain adaptation (MSDA) methods aim to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Although current methods achieve target joint distribution identifiability by enforcing minimal changes across domains, they often necessitate stringent conditions, such as an adequate number of domains, monotonic transformation of latent variables, and invariant label distributions. These requirements are challenging to satisfy in real-world applications. To mitigate the need for these strict assumptions, we propose a subspace identification theory that guarantees the disentanglement of domain-invariant and domain-specific variables under less restrictive constraints regarding domain numbers and transformation properties and thereby facilitating domain adaptation by minimizing the impact of domain shifts on invariant variables. Based on this theory, we develop a Subspace Identification Guarantee (SIG) model that leverages variational inference. Furthermore, the SIG model incorporates class-aware conditional alignment to accommodate target shifts where label distributions change with the domain. Experimental results demonstrate that our SIG model outperforms existing MSDA techniques on various benchmark datasets, highlighting its effectiveness in real-world applications.

Author Information

Zijian Li (Guangdong University of Technology)
Ruichu Cai (Guangdong University of Technology)
Guangyi Chen (MBZUAI&CMU)
Boyang Sun (Mohamed bin Zayed University of Artificial Intelligence)
Zhifeng Hao (Foshan University)
Kun Zhang (CMU & MBZUAI)

More from the Same Authors