paper-with-me

홈 › Papers

Unpicking Data at the Seams: VAEs, Disentanglement and Independent Components

2024-10-29 · Carl Allen

Disentanglement, or identifying salient statistically independent factors of the data, is of interest in many areas of machine learning and statistics, such as synthetic data generation with controlled properties, robust classification of features, parsimonious encoding, and improving our understanding of the generative process underlying the data. Disentanglement is observed in several generative paradigms, including Variational Autoencoders (VAEs), Generative Adversarial Networks and diffusion models. Particular progress has recently been made in understanding disentanglement in VAEs, where the choice of diagonal posterior covariance matrices is proposed to promote mutual orthogonality between columns of the decoder's Jacobian. We continue this thread to show how such linear independence translates to statistical independence, completing the chain in understanding how the VAE's objective identifies independent components of, or disentangles, the data.

📄 PDF Abstract BibTeX arXiv:2410.22559

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementRobust classificationSynthetic Data Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization

2021-06-05 · NeurIPS 2021 12 · Travers Rhodes, Daniel D. Lee

There have been many recent advances in representation learning; however, unsupervised representation learning can still struggle with model identification issues related to rotations of the latent space. Variational Aut…

DisentanglementRepresentation Learning

Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder

2022-10-18 · Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran

Out-of-distribution (OOD) detection, i.e., finding test samples derived from a different distribution than the training set, as well as reasoning about such samples (OOD reasoning), are necessary to ensure the safety of …

DisentanglementOut of Distribution (OOD) Detection

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs

2025-05-30 · Zihao Chen, Yu Xiang, Wenyong Wang

Despite the success in learning semantically meaningful, unsupervised disentangled representations, variational autoencoders (VAEs) and their variants face a fundamental theoretical challenge: substantial evidence indica…

DisentanglementInductive Bias

CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder

2024-01-17 · Hee-Jun Jung, Jaehyoung Jeong, Kangil Kim

Symmetries of input and latent vectors have provided valuable insights for disentanglement learning in VAEs. However, only a few works were proposed as an unsupervised method, and even these works require known factor in…

DecoderDisentanglementInductive Bias

Disentanglement by means of action-induced representations

2026-02-06 · Gorka Muñoz-Gil, Hendrik Poulsen Nautrup, Arunava Majumder, Paulin de Schoulepnikoff 외 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 corre…

Representation Learning