More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication
Abstract
Task-oriented communication improves communication efficiency by transmitting semantic information required for downstream tasks, but may incur redundancy with previously transmitted information. To address this issue, we propose a variational directed information bottleneck joint source-channel coding (VDIB-JSCC) framework that transmits only previously unacquired information. Specifically, we use directed information to characterize the causal flow of task-relevant incremental information and theoretically demonstrate its advantages over mutual information and conditional mutual information. Based on this metric, we formulate a directed information bottleneck (DIB) objective that balances task-relevant information preservation and redundant information compression. We further derive a variational formulation, termed VDIB, whose tractable upper bound serves as the training loss. The encoder integrates a Vision Transformer for frame-wise semantic extraction and a Mamba-based causal state-space model for capturing temporal dependencies and extracting incremental information, while the decoder uses a Mamba-based state-space model for task inference. Experiments on CIFAR-10 and CIFAR-100 video streams demonstrate that VDIB-JSCC achieves higher classification accuracy with less transmitted information than state-of-the-art semantic communication methods. These results show that leveraging historical knowledge enables task completion with less information, improving communication efficiency.
Related
- Energy-Efficient UAV Covert Communications via Metaheuristic Optimization
- On the Information Bottleneck for Stable Variables
- Dynamics Aware Past-Future Information Bottleneck
- Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis
- On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck
BibTeX
@misc{zheng2026more,
title = {{More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication}},
author = {Zhirun Zheng and Yiqin Deng and Phone Lin and Yuguang Fang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16328},
eprint = {2610.16328},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16328},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - More Interactions Make Communications More Efficient: A Directed Information Bottleneck Approach to Task-Oriented Communication
AU - Zhirun Zheng
AU - Yiqin Deng
AU - Phone Lin
AU - Yuguang Fang
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.16328
UR - https://arxiv.org/abs/2610.16328
AB - Task-oriented communication improves communication efficiency by transmitting semantic information required for downstream tasks, but may incur redundancy with previously transmitted information. To address this issue, we propose a variational directed information bottleneck joint source-channel coding (VDIB-JSCC) framework that transmits only previously unacquired information. Specifically, we use directed information to characterize the causal flow of task-relevant incremental information and theoretically demonstrate its advantages over mutual information and conditional mutual information. Based on this metric, we formulate a directed information bottleneck (DIB) objective that balances task-relevant information preservation and redundant information compression. We further derive a variational formulation, termed VDIB, whose tractable upper bound serves as the training loss. The encoder integrates a Vision Transformer for frame-wise semantic extraction and a Mamba-based causal state-space model for capturing temporal dependencies and extracting incremental information, while the decoder uses a Mamba-based state-space model for task inference. Experiments on CIFAR-10 and CIFAR-100 video streams demonstrate that VDIB-JSCC achieves higher classification accuracy with less transmitted information than state-of-the-art semantic communication methods. These results show that leveraging historical knowledge enables task completion with less information, improving communication efficiency.
ER -