Unsupervised disentanglement of content and style via variance-invariance constraints
Wu, Yuxuan Wang, Ziyu Raj, Bhiksha Xia, Gus
Wu, Yuxuan
Wang, Ziyu
Raj, Bhiksha
Xia, Gus
Author
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
We contribute an unsupervised method that effectively learns disentangled content and style representations from sequences of observations. Unlike most disentanglement algorithms that rely on domain-specific labels or knowledge, our method is based on the insight of domain-general statistical differences between content and style - content varies more among different fragments within a sample but maintains an invariant vocabulary across data samples, whereas style remains relatively invariant within a sample but exhibits more significant variation across different samples. We integrate such inductive bias into an encoder-decoder architecture and name our method after V3 (variance-versus-invariance). Experimental results show that V3 generalizes across multiple domains and modalities, successfully learning disentangled content and style representations, such as pitch and timbre from music audio, digit and color from images of hand-written digits, and action and character appearance from simple animations. V3 demonstrates strong disentanglement performance compared to existing unsupervised methods, along with superior out-of-distribution generalization under few-shot adaptation compared to supervised counterparts. Lastly, symbolic-level interpretability emerges in the learned content codebook, forging a near one-to-one alignment between machine representation and human knowledge. © 2025 13th International Conference on Learning Representations, ICLR 2025. All rights reserved.
Citation
Y. Wu, Z. Wang, ♯♭ Bhiksha, ♮♭ R., G. Xia, and ♭♯ ♭ Mohamed, “Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints,” International Conference on Representation Learning, vol. 2025, pp. 45518–45543, May 2025
Source
13th International Conference on Learning Representations, ICLR 2025
Conference
13th International Conference on Learning Representations, ICLR 2025
Keywords
Subjects
Source
13th International Conference on Learning Representations, ICLR 2025
Publisher
International Conference on Learning Representations, ICLR