Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
Sprache des Titels:
A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regular- ization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distributions. The proposed metric re- sults from modifying an integral probability metric such that it becomes less translation- sensitive on a polynomial function space. The metric has an intuitive interpretation in the dual space as the sum of differences of higher order central moments of the corresponding activation distributions. Under appropriate assumptions on the input distributions, error minimization is proven for the continuous case. As demonstrated by an analysis of stan- dard benchmark experiments for sentiment analysis, object recognition and digit recog- nition, the outlined approach is robust regarding parameter changes and achieves higher classification accuracies than comparable approaches.