Official PyTorch implementation of Fully Attentional Networks

This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.

Pytorch implementation of Deep Variational Information Bottleneck

Graph Information Bottleneck (GIB) for learning minimal sufficient structural and feature information using GNNs

This is the official repository for our CVPR 2023 paper 'Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification'.

Official repo for PAC-Bayes Information Bottleneck. ICLR 2022.

Pytorch Implementation of the Nonlinear Information Bottleneck

[ICDE 2022]Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

[ICML'24] Official PyTorch Implementation of TimeX++

Microbiome-based disease prediction with multimodal variational information bottlenecks, Grazioli et al., PLOS Computational Biology 2022

Code for "Attentive Variational Information Bottleneck for TCR-peptide Interaction Prediction", Grazioli et al., Bioinformatics 2022

Project for the Large Scale Optimization course at Skoltech

Implementation of Information Bottleneck with Mutual Information Neural Estimation (MINE)

About Codes for ACL 2023 paper: Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling.

[ICMLW 2023, IEEE CISS 2024] Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy

The official repository for AAAI 2024 Oral paper "Structured Probabilistic Coding".

DVIB is an information bottleneck method that tries to disentangle multiview data into shared and private representations.

[IJCNN 2021] Structure-Aware Hierarchical Graph Pooling using Information Bottleneck

A pytorch implementation of DVIB(Deep Variational Information Bottleneck)

[AAAI 2026] InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck

Package for information-theoretic data analysis

A Python library for calculating and visualizing mutual information in neural networks. This repository includes methods to calculate mutual information using various techniques (binning, KDE, Kraskov) and tools to train neural networks and plot information plane dynamics.

Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs among Complexity, Leakage, and Utility

A Python implementation of the Information Bottleneck analysis framework (Tishby, Pereira, Bialek 2000), especially geared towards the analysis of concrete, finite-size data sets. **GitHub mirror**: development happens at https://gitlab.com/epiasini/embo

[NeurIPS] Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes

This repository hosts a progressive series of implementations (Code_v1, Code_v2, and beyond) for deterministic β*-optimization in the Information Bottleneck framework. Includes symbolic fusion, multi-path inference, and Alpay Algebra–driven critical point validation (β* = 4.14144).

Information bottleneck's (IB) principle applied to categorical data clustering.

Modeled discriminative prior problem learning privacy-utility trade-off Private Information Bottleneck un-supervised

Investigating DRL DCVAE} for mitigating 15% domain shift in cardiac MRI segmentation. Conclusively proves the Information Bottleneck trade-off: 0.02 generalization gap vs. 0.25 DSC performance. Structural limits of DRL identified for high-detail medical tasks.

Information Bottleneck as Optimisation Method for SSVEP-Based BCI