Information Bottleneck

Also known as IB

Overview

Information Bottleneck methods seek compact representations that preserve information relevant to a task while discarding irrelevant details. Common approaches include variational and conditional bottlenecks, mutual-information or rate-distortion objectives, and contrastive or structured regularizers. They are used in learning robust features, protecting privacy, explaining predictions, and limiting communication or memory in agents and multimodal systems. A central challenge is choosing and optimizing the compression level: too little compression retains nuisance information, while too much removes evidence needed for the task, and the right balance depends on the setting.

Latest papers

CardsList

62 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Distributed Information Bottleneck Theory for Multi-Modal Task-Aware Semantic Communication

    Oct 5, 2025Yujie Zhou, Cheng Peng, Rulong Wang +4Task-Oriented Semantic CommunicationInformation Bottleneck

  2. VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR

    May 23, 2025Shenghui Chen, Po-han Li, Sandeep Chinchali +1Information BottleneckVideo Summarization