Learning Correlated Latent Representations with Adaptive Priors
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed Correlated Variational Auto-Encoders (CVAEs), which employ a structured mixture model as prior and a structured variational posterior for each mixture component to enforce that the learned latent representations follow the same correlation structure. However, as we demonstrate in this work, such a choice cannot guarantee that CVAEs capture all the correlations. Furthermore, it prevents us from obtaining a tractable joint and marginal variational distribution. To address these issues, we propose Adaptive Correlated Variational Auto-Encoders (ACVAEs), which apply an adaptive prior distribution that can be adjusted during training and can learn a tractable joint variational distribution. Its tractable form also enables further refinement with belief propagation. Experimental results on link prediction and hierarchical clustering show that ACVAEs significantly outperform CVAEs among other benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringLink PredictionSimilar Papers 제목 키워드 기반
Inference with correlated priors using sisters cells
A common view of sensory processing is as probabilistic inference of latent causes from receptor activations. Standard approaches often assume these causes are a priori independent, yet real-world generative factors are …
Multi-scale and Context-adaptive Entropy Model for Image Compression
We propose an end-to-end trainable image compression framework with a multi-scale and context-adaptive entropy model, especially for low bitrate compression. Due to the success of autoregressive priors in probabilistic g…
Image CompressionMS-SSIMSSIMDecoupled Sparse Priors Guided Diffusion Compression Model for Point Clouds
Lossy compression methods rely on an autoencoder to transform a point cloud into latent points for storage, leaving the inherent redundancy of latent representations unexplored. To reduce redundancy in latent points, we …
DecoderRL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models
Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-of-domain tasks. Recent test-time steering and scaling methods improv…
Reinforcement LearningOffline RLDegradation-Aware All-in-One Image Restoration via Latent Prior Encoding
Real-world images often suffer from spatially diverse degradations such as haze, rain, snow, and low-light, significantly impacting visual quality and downstream vision tasks. Existing all-in-one restoration (AIR) approa…
Image Restoration