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

• URL: http://arxiv.org/abs/2106.02923v1
• Date: Sat, 5 Jun 2021 15:40:55 GMT
• Title: Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization
• Authors: Travers Rhodes, Daniel D. Lee
• Abstract summary: Variational Auto-Encoders (VAEs) and their extensions have been shown to align latent variables with PCA directions. We propose applying an $L_$1 loss to the VAE's generative Jacobian during training to encourage local latent variable alignment.
• Score: 21.80539548847009
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: There have been many recent advances in representation learning; however, unsupervised representation learning can still struggle with model identification issues. Variational Auto-Encoders (VAEs) and their extensions such as $\beta$-VAEs have been shown to locally align latent variables with PCA directions, which can help to improve model disentanglement under some conditions. Borrowing inspiration from Independent Component Analysis (ICA) and sparse coding, we propose applying an $L_1$ loss to the VAE's generative Jacobian during training to encourage local latent variable alignment with independent factors of variation in the data. We demonstrate our results on a variety of datasets, giving qualitative and quantitative results using information theoretic and modularity measures that show our added $L_1$ cost encourages local axis alignment of the latent representation with individual factors of variation.

Related papers

• $α$-TCVAE: On the relationship between Disentanglement and Diversity [21.811889512977924]
  In this work, we introduce $alpha$-TCVAE, a variational autoencoder optimized using a novel total correlation (TC) lower bound. We present quantitative analyses that support the idea that disentangled representations lead to better generative capabilities and diversity. Our results demonstrate that $alpha$-TCVAE consistently learns more disentangled representations than baselines and generates more diverse observations.
  arXiv  Detail & Related papers  (2024-11-01T13:50:06Z)
• Delta-AI: Local objectives for amortized inference in sparse graphical models [64.5938437823851]
  We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. We illustrate $Delta$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.
  arXiv  Detail & Related papers  (2023-10-03T20:37:03Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Learning Conditional Invariance through Cycle Consistency [60.85059977904014]
  We propose a novel approach to identify meaningful and independent factors of variation in a dataset. Our method involves two separate latent subspaces for the target property and the remaining input information. We demonstrate on synthetic and molecular data that our approach identifies more meaningful factors which lead to sparser and more interpretable models.
  arXiv  Detail & Related papers  (2021-11-25T17:33:12Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Demystifying Inductive Biases for $\beta$-VAE Based Architectures [19.53632220171481]
  We shed light on the inductive bias responsible for the success of VAE-based architectures. We show that in classical datasets the structure of variance, induced by the generating factors, is conveniently aligned with the latent directions fostered by the VAE objective.
  arXiv  Detail & Related papers  (2021-02-12T23:57:20Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)
• NestedVAE: Isolating Common Factors via Weak Supervision [45.366986365879505]
  We identify the connection between the task of bias reduction and that of isolating factors common between domains. To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory. Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempts to reconstruct the latent representation of one image, from the latent representation of its paired image.
  arXiv  Detail & Related papers  (2020-02-26T15:49:57Z)
• On Implicit Regularization in $\beta$-VAEs [32.674190005384204]
  We study the regularizing effects of variational distributions on learning in generative models from two perspectives. First, we analyze the role that the choice of variational family plays in uniqueness to the learned model by restricting the set of optimal generative models. Second, we study the regularization effect of the variational family on the local geometry of the decoding model.
  arXiv  Detail & Related papers  (2020-01-31T19:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.