Disentanglement of Correlated Factors via Hausdorff Factorized SupportDownload PDF

Anonymous

22 Sept 2022, 12:39 (modified: 09 Nov 2022, 15:24)ICLR 2023 Conference Blind SubmissionReaders: Everyone
Keywords: disentanglement, representation learning, generalization
TL;DR: We develop a method that allows for disentangled representation learning not only under the assumption of independent factors of variation but instead fundamentally allows for much more realistic correlations during training.
Abstract: A grand goal in deep learning research is to learn representations capable of generalizing across distribution shifts. Disentanglement is one promising direction aimed at aligning a model’s representations with the underlying factors generating the data (e.g. color or background). Existing disentanglement methods, however, rely on an often unrealistic assumption: that factors are statistically independent. In reality, factors (like object color and shape) are correlated. To address this limitation, we propose a relaxed disentanglement criterion – the Hausdorff Factorized Support (HFS) criterion – that encourages a factorized support, rather than a factorial distribution, by minimizing a Hausdorff distance. This allows for arbitrary distributions of the factors over their support, including correlations between them. We show that the use of HFS consistently facilitates disentanglement and recovery of ground-truth factors across a variety of correlation settings and benchmarks, even under severe training correlations and correlation shifts, with in parts over +60% in relative improvement over existing disentanglement methods. In addition, we find that leveraging HFS for representation learning can even facilitate transfer to downstream tasks such as classification under distribution shifts. We hope our original approach and positive empirical results inspire further progress on the open problem of robust generalization.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
10 Replies

Loading