Network Architecture Search for Domain Adaptation
This work addresses domain adaptation for machine learning applications by improving transferable representations, though it appears incremental as it builds on existing neural architecture search methods.
The paper tackled the problem of sub-optimal domain adaptation performance by proposing NASDA, a framework that uses neural architecture search to find optimal network architectures, achieving state-of-the-art results on multiple benchmarks.
Deep networks have been used to learn transferable representations for domain adaptation. Existing deep domain adaptation methods systematically employ popular hand-crafted networks designed specifically for image-classification tasks, leading to sub-optimal domain adaptation performance. In this paper, we present Neural Architecture Search for Domain Adaptation (NASDA), a principle framework that leverages differentiable neural architecture search to derive the optimal network architecture for domain adaptation task. NASDA is designed with two novel training strategies: neural architecture search with multi-kernel Maximum Mean Discrepancy to derive the optimal architecture, and adversarial training between a feature generator and a batch of classifiers to consolidate the feature generator. We demonstrate experimentally that NASDA leads to state-of-the-art performance on several domain adaptation benchmarks.