Forget-me-not! Contrastive Critics for Mitigating Posterior Collapse
Variational autoencoders (VAEs) suffer from posterior collapse, where the powerful neural networks used for modeling and inference optimize the objective without meaningfully using the latent representation. We introduce inference critics that detect and incentivize against posterior collapse by requiring correspondence between latent variables and the observations. By connecting the critic's objective to the literature in self-supervised contrastive representation learning, we show both theoretically and empirically that optimizing inference critics increases the mutual information between observations and latents, mitigating posterior collapse. This approach is straightforward to implement and requires significantly less training time than prior methods, yet obtains competitive results on three established datasets. Overall, the approach lays the foundation to bridge the previously disconnected frameworks of contrastive learning and probabilistic modeling with variational autoencoders, underscoring the benefits both communities may find at their intersection.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse
The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated…
SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where las…
Continual LearningPosterior Collapse and Latent Variable Non-identifiability
Variational autoencoders model high-dimensional data by positing low-dimensional latent variables that are mapped through a flexible distribution parametrized by a neural network. Unfortunately, variational autoencoders …
AttributeVariational InferenceMitigating Mode Collapse by Sidestepping Catastrophic Forgetting
Generative Adversarial Networks (GANs) are a class of generative models used for various applications, but they have been known to suffer from the mode collapse problem, in which some modes of the target distribution are…
Continual LearningLearning with Reflective Likelihoods
Models parameterized by deep neural networks have achieved state-of-the-art results in many domains. These models are usually trained using the maximum likelihood principle with a finite set of observations. H…
Attribute