A Discriminative Technique for Multiple-Source Adaptation
This provides a more practical solution for domain adaptation when multiple source domains are available, though it appears to be an incremental improvement over existing methods.
The authors tackled the multiple-source adaptation problem by developing a discriminative technique that requires only conditional probabilities instead of full density estimation. Their algorithm outperformed previous generative solutions and other domain adaptation baselines in real-world applications.
We present a new discriminative technique for the multiple-source adaptation, MSA, problem. Unlike previous work, which relies on density estimation for each source domain, our solution only requires conditional probabilities that can easily be accurately estimated from unlabeled data from the source domains. We give a detailed analysis of our new technique, including general guarantees based on Rényi divergences, and learning bounds when conditional Maxent is used for estimating conditional probabilities for a point to belong to a source domain. We show that these guarantees compare favorably to those that can be derived for the generative solution, using kernel density estimation. Our experiments with real-world applications further demonstrate that our new discriminative MSA algorithm outperforms the previous generative solution as well as other domain adaptation baselines.