AR-Flow VAE: A Structured Autoregressive Flow Prior Variational Autoencoder for Unsupervised Blind Source Separation

2026-03-15

AI Summary

This work proposes a novel variational autoencoder framework for unsupervised blind source separation, which effectively captures the non-Gaussianity and temporal dependencies of latent source signals by introducing parameter-adaptive autoregressive flow priors for each source. The method leverages structured heterogeneous prior constraints to encourage distinct latent dimensions to correspond to different source signals, thereby enabling end-to-end disentanglement and separation. Experimental results demonstrate that the proposed architecture significantly outperforms existing approaches in blind source separation tasks, achieving superior separation performance while also providing theoretical support for model identifiability and interpretability.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Reasoning under Uncertainty: Relational Probabilistic Models
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Blind source separation (BSS) seeks to recover latent source signals from observed mixtures. Variational autoencoders (VAEs) offer a natural perspective for this problem: the latent variables can be interpreted as source components, the encoder can be viewed as a demixing mapping from observations to sources, and the decoder can be regarded as a remixing process from inferred sources back to observations. In this work, we propose AR-Flow VAE, a novel VAE-based framework for BSS in which each latent source is endowed with a parameter-adaptive autoregressive flow prior. This prior significantly enhances the flexibility of latent source modeling, enabling the framework to capture complex non-Gaussian behaviors and structured dependencies, such as temporal correlations, that are difficult to represent with conventional priors. In addition, the structured prior design assigns distinct priors to different latent dimensions, thereby encouraging the latent components to separate into different source signals under heterogeneous prior constraints. Experimental results validate the effectiveness of the proposed architecture for blind source separation. More importantly, this work provides a foundation for future investigations into the identifiability and interpretability of AR-Flow VAE.

Problem

• Blind Source Separation
• Unsupervised Learning
• Latent Source Recovery
• Non-Gaussian Modeling
• Temporal Dependencies

Innovation

• autoregressive flow
• structured prior
• blind source separation
• variational autoencoder
• non-Gaussian modeling