Awesome-Information-Bottleneck

Awesome-Information-Bottleneck

信息瓶颈理论在机器学习中的进展和应用综述

本项目汇总了信息瓶颈理论在机器学习领域的关键文献,包括经典论文、综述、理论研究、模型开发和应用。重点介绍了信息瓶颈原理解释深度神经网络学习行为的方法,以及在表示学习、生成模型、强化学习等方向的创新应用。项目为研究人员和实践者提供了了解信息瓶颈理论最新进展的全面资源。

Information Bottleneck深度学习信息理论神经网络机器学习Github开源项目

Awesome Information Bottleneck Paper List Awesome PRs Welcome

In memory of Professor Naftali Tishby.
Last updated on October, 2022. <br>

0. Introduction

illustration To learn, you must forget. This may probably be one of the most intuitive lessons we have from Naftali Tishby's Information Bottleneck (IB) methods, which grew out of the fundamental tradeoff (rate v.s. distortion) from Claude Shannon's information theory, and later creatively explained the learning behaviors of deep neural networks by the fitting & compression framework.

It has been four years since the dazzling talk on Opening the Black Box of Deep Neural Networks, and more than twenty years since the first paper on the Information Bottleneck method. It is time for us to take a look back, to celebrate what has been established, and to prepare for a future.

This repository is organized as follows:

All papers are selected and sorted by topic/conference/year/importance. Please send a pull request if you would like to add any paper.

We also made slides on theory, applications and controversy for the initial Information Bottleneck principle in deep learning (p.s., some controversy has been addressed by recent publications, e.g., Lorenzen et al., 2021).

1. Classics

Agglomerative Information Bottleneck [link]
Noam Slonim, Naftali Tishby
NIPS, 1999 <br>

🐤 The Information Bottleneck Method [link]
Naftali Tishby, Fernando C. Pereira, William Bialek
Preprint, 2000 <br>

Predictability, complexity and learning [link]
William Bialek, Ilya Nemenman, Naftali Tishby
Neural Computation, 2001 <br>

Sufficient Dimensionality Reduction: A novel analysis principle [link]
Amir Globerson, Naftali Tishby
ICML, 2002 <br>

The information bottleneck: Theory and applications [link]
Noam Slonim
PhD Thesis, 2002 <br>

An Information Theoretic Tradeoff between Complexity and Accuarcy [link]
Ran Gilad-Bachrach, Amir Navot, Naftali Tishby
COLT, 2003 <br>

Information Bottleneck for Gaussian Variables [link]
Gal Chechik, Amir Globerson, Naftali Tishby, Yair Weiss
NIPS, 2003 <br>

Information and Fitness [link]
Samuel F. Taylor, Naftali Tishby and William Bialek
Preprint, 2007 <br>

Efficient representation as a design principle for neural coding and computation [link]
William Bialek, Rob R. de Ruyter van Steveninck, and Naftali Tishby
Preprint, 2007 <br>

The Information Bottleneck Revisited or How to Choose a Good Distortion Measure [link]
Peter Harremoes and Naftali Tishby
ISIT, 2007 <br>

🐤 Learning and Generalization with the Information Bottleneck [link]
Ohad Shamir, Sivan Sabato, Naftali Tishby
Journal of Theoretical Computer Science, 2009 <br>

🐤 Information-Theoretic Bounded Rationality [link]
Pedro A. Ortega, Daniel A. Braun, Justin Dyer, Kee-Eung Kim, Naftali Tishby
Preprint, 2015 <br>

🐤 Opening the Black Box of Deep Neural Networks via Information [link]
Ravid Shwartz-Ziv, Naftali Tishby
ICRI, 2017 <br>

2. Reviews

Information Bottleneck and its Applications in Deep Learning [link]
Hassan Hafez-Kolahi, Shohreh Kasaei
Preprint, 2019 <br>

The Information Bottleneck Problem and Its Applications in Machine Learning [link]
Ziv Goldfeld, Yury Polyanskiy
Preprint, 2020 <br>

On the Information Bottleneck Problems: Models, Connections, Applications and Information Theoretic Views [link]
Abdellatif Zaidi, Iñaki Estella-Aguerri, Shlomo Shamai
Entropy, 2020 <br>

Information Bottleneck: Theory and Applications in Deep Learning [link]
Bernhard C. Geiger, Gernot Kubin
Entropy, 2020 <br>

On Information Plane Analyses of Neural Network Classifiers – A Review [link]
Bernhard C. Geiger
Preprint, 2021

Table 1 (p.2) gives a nice summary on the effect of different architectures & MI estimators on the existence of the compression phases and causal links between compression and generalizations.

A Critical Review of Information Bottleneck Theory and its Applications to Deep Learning [link]
Mohammad Ali Alomrani
Preprint, 2021 <br>

Information Flow in Deep Neural Networks [link]
Ravid Shwartz-Ziv
PhD Thesis, 2022 <br>

3. Theories

Gaussian Lower Bound for the Information Bottleneck Limit [link]
Amichai Painsky, Naftali Tishby
JMLR, 2017 <br>

Information-theoretic analysis of generalization capability of learning algorithms [link]
Aolin Xu, Maxim Raginsky
NeurIPS, 2017 <br>

Caveats for information bottleneck in deterministic scenarios [link] [ICLR version]
Artemy Kolchinsky, Brendan D. Tracey, Steven Van Kuyk
UAI, 2018 <br>

🐤🔥 Emergence of Invariance and Disentanglement in Deep Representations [link]
Alessandro Achille, Stefano Soatto
JMLR, 2018

  • This paper is a gem. On a high-level, it shows the relationship of generalization and information bottleneck in weights (IIW).
    • Be aware how this differs from Tishby's original definition on information bottleneck in representation).
  • Specifically, if we approximate SGD by stochastic differential equations, we can see that SGD naturally leads to minimization in IIW.
  • The authors argue that an optimal representation should have 4 properties: sufficiency, minimality, invariance, and disentanglement. Notably, the last two properties can naturally emerge with the minimization in mutual information between the datasets and network weights, or IIW.
<br>

On the Information Bottleneck Theory of Deep Learning [link]
Andrew Michael Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan Daniel Tracey, David Daniel Cox
ICLR, 2018 <br>

The Dual Information Bottleneck [link]
Zoe Piran, Ravid Shwartz-Ziv, Naftali Tishby
Preprint, 2019 <br>

🐤 Learnability for the Information Bottleneck [link] [slides] [poster] [journal version] [workshop version]
Tailin Wu, Ian Fischer, Isaac L. Chuang, Max Tegmark
UAI, 2019 <br>

🐤 Phase Transitions for the Information Bottleneck in Representation Learning [link] [video]
Tailin Wu, Ian Fischer
ICLR, 2020 <br>

Bottleneck Problems: Information and Estimation-Theoretic View [link]
Shahab Asoodeh, Flavio Calmon
Preprint, 2020 <br>

Information Bottleneck: Exact Analysis of (Quantized) Neural Networks [link]
Stephan Sloth Lorenzen, Christian Igel, Mads Nielsen
Preprint, 2021

  • This paper shows that different ways of binning when computing the mutual information leads to qualitatively different results.
  • It then confirms then original IB paper's results of the fitting & compression phase using quantized nets with exact computation for mutual information.
<br>

Perturbation Theory for the Information Bottleneck [link]
Vudtiwat Ngampruetikorn, David J. Schwab
Preprint, 2021 <br>

PAC-Bayes Information Bottleneck [link]
Zifeng Wang, Shao-Lun Huang, Ercan Engin Kuruoglu, Jimeng Sun, Xi Chen, Yefeng Zheng
ICLR, 2022

  • This paper discusses using $I(w, S)$ instead to $I(T, X)$ as the information bottleneck.
  • However, activations should in effect play a crucial role in network's generalization, but they are not explicitly captured by $I(w, S)$.
<br>

4. Models

Deep Variational Information Bottleneck [link]
Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy
ICLR, 2017 <br>

The Deterministic Information Bottleneck [link] [UAI Version]
DJ Strouse, David J. Schwab
Neural Computation, 2017

This replaces the mutual information term with entropy in the original IB objective.

<br>

Learning Sparse Latent Representations with the Deep Copula Information Bottleneck [link]
Aleksander Wieczorek, Mario Wieser, Damian Murezzan, Volker Roth
ICLR, 2018 <br>

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck [link]
Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
NeurIPS, 2019 <br>

Information bottleneck through variational glasses [link]
Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar, Olga Taran, Taras Holotyak, Danilo Jimenez Rezende
NeurIPS Bayesian Deep Learning Workshop, 2019 <br>

🐤 Variational Discriminator Bottleneck [link]
Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine
ICLR, 2019 <br>

Nonlinear Information Bottleneck [link]
Artemy Kolchinsky, Brendan Tracey, David Wolpert
Entropy, 2019

This formuation shows better performance than VIB.

<br>

General Information Bottleneck Objectives and their Applications to Machine Learning [link]
Sayandev Mukherjee
Preprint, 2019

This paper synthesize IB and Predictive IB, and provides a new variational bound.

<br>

🐤 Graph Information Bottleneck [link] [code] [slides]
Tailin Wu, Hongyu Ren, Pan Li, Jure Leskovec,
NeurIPS, 2020 <br>

🐤 Learning Optimal Representations with the Decodable Information Bottleneck [link]
Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam
NeurIPS, 2020 <br>

🐤 Concept Bottleneck Models [link]
Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, Percy Liang
ICML, 2020 <br>

Disentangled Representations for Sequence Data using Information Bottleneck Principle [link] [talk]
Masanori Yamada, Heecheol Kim, Kosuke Miyoshi, Tomoharu Iwata, Hiroshi Yamakawa
ICML, 2020 <br>

🐤 IBA: Restricting the Flow: Information Bottlenecks for Attribution

编辑推荐精选

讯飞智文

讯飞智文

一键生成PPT和Word,让学习生活更轻松

讯飞智文是一个利用 AI 技术的项目,能够帮助用户生成 PPT 以及各类文档。无论是商业领域的市场分析报告、年度目标制定,还是学生群体的职业生涯规划、实习避坑指南,亦或是活动策划、旅游攻略等内容,它都能提供支持,帮助用户精准表达,轻松呈现各种信息。

AI办公办公工具AI工具讯飞智文AI在线生成PPTAI撰写助手多语种文档生成AI自动配图热门
讯飞星火

讯飞星火

深度推理能力全新升级,全面对标OpenAI o1

科大讯飞的星火大模型,支持语言理解、知识问答和文本创作等多功能,适用于多种文件和业务场景,提升办公和日常生活的效率。讯飞星火是一个提供丰富智能服务的平台,涵盖科技资讯、图像创作、写作辅助、编程解答、科研文献解读等功能,能为不同需求的用户提供便捷高效的帮助,助力用户轻松获取信息、解决问题,满足多样化使用场景。

热门AI开发模型训练AI工具讯飞星火大模型智能问答内容创作多语种支持智慧生活
Spark-TTS

Spark-TTS

一种基于大语言模型的高效单流解耦语音令牌文本到语音合成模型

Spark-TTS 是一个基于 PyTorch 的开源文本到语音合成项目,由多个知名机构联合参与。该项目提供了高效的 LLM(大语言模型)驱动的语音合成方案,支持语音克隆和语音创建功能,可通过命令行界面(CLI)和 Web UI 两种方式使用。用户可以根据需求调整语音的性别、音高、速度等参数,生成高质量的语音。该项目适用于多种场景,如有声读物制作、智能语音助手开发等。

Trae

Trae

字节跳动发布的AI编程神器IDE

Trae是一种自适应的集成开发环境(IDE),通过自动化和多元协作改变开发流程。利用Trae,团队能够更快速、精确地编写和部署代码,从而提高编程效率和项目交付速度。Trae具备上下文感知和代码自动完成功能,是提升开发效率的理想工具。

AI工具TraeAI IDE协作生产力转型热门
咔片PPT

咔片PPT

AI助力,做PPT更简单!

咔片是一款轻量化在线演示设计工具,借助 AI 技术,实现从内容生成到智能设计的一站式 PPT 制作服务。支持多种文档格式导入生成 PPT,提供海量模板、智能美化、素材替换等功能,适用于销售、教师、学生等各类人群,能高效制作出高品质 PPT,满足不同场景演示需求。

讯飞绘文

讯飞绘文

选题、配图、成文,一站式创作,让内容运营更高效

讯飞绘文,一个AI集成平台,支持写作、选题、配图、排版和发布。高效生成适用于各类媒体的定制内容,加速品牌传播,提升内容营销效果。

热门AI辅助写作AI工具讯飞绘文内容运营AI创作个性化文章多平台分发AI助手
材料星

材料星

专业的AI公文写作平台,公文写作神器

AI 材料星,专业的 AI 公文写作辅助平台,为体制内工作人员提供高效的公文写作解决方案。拥有海量公文文库、9 大核心 AI 功能,支持 30 + 文稿类型生成,助力快速完成领导讲话、工作总结、述职报告等材料,提升办公效率,是体制打工人的得力写作神器。

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

下拉加载更多