Abstract | ||
---|---|---|
Finding domain invariant features is critical for successful domain adaptation and transfer learning. However, in the case of unsupervised adaptation, there is a significant risk of overfitting on source training data. Recently, a regularization for domain adaptation was proposed for deep models by (Ganin and Lempitsky, 2015). We build on their work by suggesting a more appropriate regularization for denoising autoencoders. Our model remains unsupervised and can be computed in a closed form. On standard text classification adaptation tasks, our approach yields the state of the art results, with an important reduction of the learning cost. |
Year | Venue | DocType |
---|---|---|
2016 | PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2016), VOL 2 | Conference |
Volume | Citations | PageRank |
P16-2 | 2 | 0.36 |
References | Authors | |
15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephane Clinchant | 1 | 102 | 10.05 |
Gabriela Csurka | 2 | 972 | 85.08 |
Boris Chidlovskii | 3 | 411 | 52.58 |