March 1st14:30 , R2014 Digiteo Shannon (660) (see location):
Pascal Germain (Université Laval, Québec)
Title: A Representation Learning Approach for Domain Adaptation
Abstract:We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behavior can be achieved in almost any feed-forward model by augmenting a gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages.
We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved.
Related Paper (to appear in JMLR): http://arxiv.org/abs/1505.07818
Contact: odalricambrym.maillard at inria.fr, guillaume.charpiat at inria.fr