Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
This work addresses a practical challenge in machine learning for scenarios involving multiple heterogeneous data sources, offering an incremental improvement over existing single-source methods.
The paper tackles the problem of multi-source heterogeneous domain adaptation, where samples come from multiple domains with different distributions and features, by proposing a Conditional Weighting Adversarial Network (CWAN) that uses a conditional weighting scheme to prioritize source domains based on their divergence from the target domain, achieving superior performance over state-of-the-art methods on four real-world datasets.
Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains. In this article, we study the multisource HDA problem and propose a conditional weighting adversarial network (CWAN) to address it. The proposed CWAN adversarially learns a feature transformer, a label classifier, and a domain discriminator. To quantify the importance of different source domains, CWAN introduces a sophisticated conditional weighting scheme to calculate the weights of the source domains according to the conditional distribution divergence between the source and target domains. Different from existing weighting schemes, the proposed conditional weighting scheme not only weights the source domains but also implicitly aligns the conditional distributions during the optimization process. Experimental results clearly demonstrate that the proposed CWAN performs much better than several state-of-the-art methods on four real-world datasets.