Inducing Interpretable Representations with Variational Autoencoders
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference. This allows us to both perform reasoning (e.g. classification) under the structural constraints of a given graphical model, and use deep generative models to deal with messy, high-dimensional domains where it is often difficult to model all the variation. Learning in this framework is carried out end-to-end with a variational objective, applying to both unsupervised and semi-supervised schemes.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationVariational InferenceSimilar Papers 제목 키워드 기반
Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders
This paper addresses the challenges of detecting anomalies in cellular networks in an interpretable way and proposes a new approach using variational autoencoders (VAEs) that learn interpretable representations of the la…
Anomaly DetectionRepresentation LearningThe LORACs prior for VAEs: Letting the Trees Speak for the Data
In variational autoencoders, the prior on the latent codes $z$ is often treated as an afterthought, but the prior shapes the kind of latent representation that the model learns. If the goal is to learn a representation t…
ClusteringInterpretable representation learning of quantum data enabled by probabilistic variational autoencoders
Interpretable machine learning is rapidly becoming a crucial tool for scientific discovery. Among existing approaches, variational autoencoders (VAEs) have shown promise in extracting the hidden physical features of some…
Interpretable Machine LearningRepresentation Learningscientific discoveryInterpretable Node Representation with Attribute Decoding
Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of node representations from graph data. In this work, we systematically analyze modeling node attributes in VGAEs and show that attrib…
AttributeRepresentation LearningNonparametric Variational Auto-encoders for Hierarchical Representation Learning
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple…
ClusteringRepresentation LearningVariational Inference