Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
This work addresses domain adaptation for machine learning practitioners by providing a method to infer domain indices, though it is incremental as it builds on prior domain index research.
The paper tackles the problem of domain adaptation when domain indices are unavailable by proposing an adversarial variational Bayesian framework that infers interpretable domain indices from multi-domain data, achieving superior performance compared to state-of-the-art methods.
Previous studies have shown that leveraging domain index can significantly boost domain adaptation performance (arXiv:2007.01807, arXiv:2202.03628). However, such domain indices are not always available. To address this challenge, we first provide a formal definition of domain index from the probabilistic perspective, and then propose an adversarial variational Bayesian framework that infers domain indices from multi-domain data, thereby providing additional insight on domain relations and improving domain adaptation performance. Our theoretical analysis shows that our adversarial variational Bayesian framework finds the optimal domain index at equilibrium. Empirical results on both synthetic and real data verify that our model can produce interpretable domain indices which enable us to achieve superior performance compared to state-of-the-art domain adaptation methods. Code is available at https://github.com/Wang-ML-Lab/VDI.