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

arXiv: https://arxiv.org/abs/2510.04000 · HTML: https://mlsanity.com/paper/2510.04000/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [CentralNet: a Multilayer Approach for Multimodal Fusion](https://mlsanity.com/paper/1808.07275/) (2018)
- [MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing](https://mlsanity.com/paper/2305.10345/) (2023)
- [Task-Oriented Multi-User Semantic Communications](https://mlsanity.com/paper/2112.10255/) (2021)
- [The Information Bottleneck Problem and Its Applications in Machine Learning](https://mlsanity.com/paper/2004.14941/) (2020)
- [From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problems](https://mlsanity.com/paper/2012.15405/) (2020)
- [Task-Oriented Communication for Multi-Device Cooperative Edge Inference](https://mlsanity.com/paper/2109.00172/) (2021)
- [Wireless Deep Video Semantic Transmission](https://mlsanity.com/paper/2205.13129/) (2022)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [A Unified Multi-Task Semantic Communication System for Multimodal Data](https://mlsanity.com/paper/2209.07689/) (2022)
- [Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis](https://mlsanity.com/paper/2205.04603/) (2022)
- [Distributed Variational Representation Learning](https://mlsanity.com/paper/1807.04193/) (2018)
- [Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation](https://mlsanity.com/paper/2209.10382/) (2022)
- [On the Information Bottleneck Problems: Models, Connections, Applications and Information Theoretic Views](https://mlsanity.com/paper/2002.00008/) (2020)
- [A Theory of Multimodal Learning](https://mlsanity.com/paper/2309.12458/) (2023)
- [Towards Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach](https://mlsanity.com/paper/2503.15764/) (2025)
- [Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning](https://mlsanity.com/paper/2210.16118/) (2022)
- [Cauchy-Schwarz Divergence Information Bottleneck for Regression](https://mlsanity.com/paper/2404.17951/) (2024)
- [Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck](https://mlsanity.com/paper/2405.09514/) (2024)
- [Rate-Adaptive Coding Mechanism for Semantic Communications With Multi-Modal Data](https://mlsanity.com/paper/2305.10773/) (2023)
- [Cooperative and Collaborative Multi-Task Semantic Communication for Distributed Sources](https://mlsanity.com/paper/2411.02150/) (2024)
- [Compression before Fusion: Broadcast Semantic Communication System for Heterogeneous Tasks](https://mlsanity.com/paper/2401.17669/) (2024)

## Built on by (most cited first, 1 of 1)

- [How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysis](https://mlsanity.com/paper/2606.13733/) (2026)

## Abstract (arXiv)

Semantic communication shifts the focus from bit-level accuracy to task-relevant semantic delivery, enabling efficient and intelligent communication for next-generation networks. However, existing multi-modal solutions often process all available data modalities indiscriminately, ignoring that their contributions to downstream tasks are often unequal. This not only leads to severe resource inefficiency but also degrades task inference performance due to irrelevant or redundant information. To tackle this issue, we propose a novel task-aware distributed information bottleneck (TADIB) framework, which quantifies the contribution of any set of modalities to given tasks. Based on this theoretical framework, we design a practical coding scheme that intelligently selects and compresses only the most task-relevant modalities at the transmitter. To find the optimal selection and the codecs in the network, we adopt the probabilistic relaxation of discrete selection, enabling distributed encoders to make coordinated decisions with score function estimation and common randomness. Extensive experiments on public datasets demonstrate that our solution matches or surpasses the inference quality of full-modal baselines while significantly reducing communication and computational costs.