KL Guided Domain Adaptation

Abstract

Domain adaptation is an important problem and often needed for real-world applications. In this problem, instead of i.i.d. training and testing datapoints, we assume that the source (training) data and the target (testing) data have different distributions. With that setting, the empirical risk minimization training procedure often does not perform well, since it does not account for the change in the distribution. A common approach in the domain adaptation literature is to learn a representation of the input that has the same (marginal) distribution over the source and the target domain. However, these approaches often require additional networks and/or optimizing an adversarial (minimax) objective, which can be very expensive or unstable in practice. To improve upon these marginal alignment techniques, in this paper, we first derive a generalization bound for the target loss based on the training loss and the reverse Kullback-Leibler (KL) divergence between the source and the target representation distributions. Based on this bound, we derive an algorithm that minimizes the KL term to obtain a better generalization to the target domain. We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples without any additional network or a minimax objective. This leads to a theoretically sound alignment method which is also very efficient and stable in practice. Experimental results also suggest that our method outperforms other representation-alignment approaches.

arXiv commentAccepted to ICLR2022

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Domain Generalization via Invariant Feature Representation
• Domain Adaptation: Learning Bounds and Algorithms
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Deep Variational Information Bottleneck
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Domain-Adversarial Neural Networks
• Bridging Theory and Algorithm for Domain Adaptation
• On Convergence and Stability of GANs
• On Learning Invariant Representation for Domain Adaptation
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• In Search of Lost Domain Generalization
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Domain Generalization for Object Recognition with Multi-task Autoencoders
• Support and Invertibility in Domain-Invariant Representations
• Domain Invariant Representation Learning with Domain Density Transformations