paper-with-me

홈 › Papers

Disentanglement by means of action-induced representations

2026-02-06 · Gorka Muñoz-Gil, Hendrik Poulsen Nautrup, Arunava Majumder, Paulin de Schoulepnikoff, Florian Fürrutter, Marius Krumm, Hans J. Briegel arxiv

Learning interpretable representations with variational autoencoders (VAEs) is a major goal of representation learning. The main challenge lies in obtaining disentangled representations, where each latent dimension corresponds to a distinct generative factor. This difficulty is fundamentally tied to the inability to perform nonlinear independent component analysis. Here, we introduce the framework of action-induced representations (AIRs) which models representations of physical systems given experiments (or actions) that can be performed on them. We show that, in this framework, we can provably disentangle degrees of freedom w.r.t. their action dependence. We further introduce a variational AIR architecture (VAIR) that can extract AIRs and therefore achieve provable disentanglement where standard VAEs fail. Beyond state representation, VAIR also captures the action dependence of the underlying generative factors, directly linking experiments to the degrees of freedom they influence.

📄 PDF Abstract BibTeX arXiv:2602.06741

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling

2024-09-09 · Stathis Megas, Daniel G. Chen, Krzysztof Polanski, Moshe Eliasof 외

Celcomen leverages a mathematical causality framework to disentangle intra- and inter- cellular gene regulation programs in spatial transcriptomics and single-cell data through a generative graph neural network. It can l…

counterfactualDisentanglementGraph Neural Network

On Disentangled Representations Learned From Correlated Data

2020-06-14 · Frederik Träuble, Elliot Creager, Niki Kilbertus, Francesco Locatello 외

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this …

DisentanglementFairness

Hyperprior Induced Unsupervised Disentanglement of Latent Representations

2018-09-12 · Abdul Fatir Ansari, Harold Soh

We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models. In contrast to current approaches that operate on the evidence lower bound (ELBO), we argue that statist…

Disentanglement

Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles

2022-06-22 · Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Linking neural representations to linguistic factors is crucial in order to build and analyze NLP models interpretable by humans. Among these factors, syntactic roles (e.g. subjects, direct objects,$\dots$) and their rea…

DecoderDisentanglementMachine TranslationSentence

Knowledge-guided Disentanglement with Atomic Actions for Action Recognition

2026-07-28 · Tianci Wu, Siqi Cao, Guangming Zhu, Jiang Lu 외 arxiv

Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures. Most existing methods rely on holistic representations, which are i…

Action Recognition