paper-with-me

홈 › Papers

Towards Better Understanding of Disentangled Representations via Mutual Information

2019-11-25 · Xiaojiang Yang, Wendong Bi, Yitong Sun, Yu Cheng, Junchi Yan

Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent. This assumption is necessary but definitely not sufficient for the disentangled representations without additional inductive biases in the modeling process, which is shown theoretically in recent studies. We argue in this work that disentangled representations should be characterized by their relation with observable data. In particular, we formulate such a relation through the concept of mutual information: the mutual information between each factor of the disentangled representations and data should be invariant conditioned on values of the other factors. Together with the widely accepted independence assumption, we further bridge it with the conditional independence of factors in representations conditioned on data. Moreover, we note that conditional independence of latent variables has been imposed on most VAE-type models and InfoGAN due to the artificial choice of factorized approximate posterior $q(\rvz|\rvx)$ in the encoders. Such an arrangement of encoders introduces a crucial inductive bias for disentangled representations. To demonstrate the importance of our proposed assumption and the related inductive bias, we show in experiments that violating the assumption leads to decline of disentanglement among factors in the learned representations.

📄 PDF Abstract BibTeX arXiv:1911.10922

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementInductive BiasRelationRepresentation Learning

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
InfoGAN InfoGAN is a type of generative adversarial network that modifies the GAN objective to encourage it to learn interpretable and…

Similar Papers 제목 키워드 기반

Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization

2022-06-02 · Mingyuan Cheng, Xinru Liao, Quan Liu, Bin Ma 외

Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies. Rece…

Causal InferencecounterfactualMulti-Task Learningregression+1

HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information

2022-08-06 · Xiao Liu, Spyridon Thermos, Pedro Sanchez, Alison Q. O'Neil 외

Learning disentangled representations requires either supervision or the introduction of specific model designs and learning constraints as biases. InfoGAN is a popular disentanglement framework that learns unsupervised …

Disentanglement

Contrastively Disentangled Sequential Variational Autoencoder

2021-10-22 · NeurIPS 2021 12 · Junwen Bai, Weiran Wang, Carla Gomes

Self-supervised disentangled representation learning is a critical task in sequence modeling. The learnt representations contribute to better model interpretability as well as the data generation, and improve the sample …

Representation Learning

A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations

2021-05-06 · ACL 2021 5 · Pierre Colombo, Chloe Clavel, Pablo Piantanida

Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others. The existent dominant approaches in th…

AttributeDisentanglementSentenceStyle Transfer+1

Mutual Information Minimization Based Disentangled Learning Framework For Causal Effect Estimation

2021-09-29 · Mingyuan Cheng

Learning treatment effect from observational data is a fundamental problem in causal inference. Recently, disentangled representation learning methods, such as DR-CFR and DeR-CFR, have witnessed great success in treatmen…

Causal InferenceRepresentation Learning