paper-with-me

홈 › Papers

Provable concept learning for interpretable predictions using variational autoencoders

2022-04-01 · Armeen Taeb, Nicolo Ruggeri, Carina Schnuck, Fanny Yang

In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations revolve around pixel-based attributions or use previously known concepts. In this paper we aim to provide explanations by provably identifying \emph{high-level, previously unknown ground-truth concepts}. To this end, we propose a probabilistic modeling framework to derive (C)oncept (L)earning and (P)rediction (CLAP) -- a VAE-based classifier that uses visually interpretable concepts as predictors for a simple classifier. Assuming a generative model for the ground-truth concepts, we prove that CLAP is able to identify them while attaining optimal classification accuracy. Our experiments on synthetic datasets verify that CLAP identifies distinct ground-truth concepts on synthetic datasets and yields promising results on the medical Chest X-Ray dataset.

📄 PDF Abstract BibTeX arXiv:2204.00492

Code (2)

nickruggeri/clap-interpretable-predictions 공식 구현 pytorch
nikruggeri/clap-interpretable-predictions 공식 구현 pytorch

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders

2023-06-28 · Amandeep Singh, Michael Weber, Markus Lange-Hegermann

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 Learning

Disentanglement by means of action-induced representations

2026-02-06 · Gorka Muñoz-Gil, Hendrik Poulsen Nautrup, Arunava Majumder, Paulin de Schoulepnikoff 외 arxiv

Learning interpretable representations with variational autoencoders (VAEs) is a major goal of representation learning. The main challenge lies in obtaining disentangled representations, where each latent dimension corre…

Representation Learning

Inducing Interpretable Representations with Variational Autoencoders

2016-11-22 · N. Siddharth, Brooks Paige, Alban Desmaison, Jan-Willem van de Meent 외

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 infere…

General ClassificationVariational Inference

Nonparametric Variational Auto-encoders for Hierarchical Representation Learning

2017-03-21 · ICCV 2017 10 · Prasoon Goyal, Zhiting Hu, Xiaodan Liang, Chenyu Wang 외

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

Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions

2023-08-24 · Kwan Ho Ryan Chan, Aditya Chattopadhyay, Benjamin David Haeffele, Rene Vidal

Variational Information Pursuit (V-IP) is a framework for making interpretable predictions by design by sequentially selecting a short chain of task-relevant, user-defined and interpretable queries about the data that ar…

Semantic SimilaritySemantic Textual Similarity