# Task-Oriented Communication for Multi-Device Cooperative Edge Inference

arXiv: https://arxiv.org/abs/2109.00172 · HTML: https://mlsanity.com/paper/2109.00172/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 30 of 30)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing](https://mlsanity.com/paper/1905.10083/) (2019)
- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)
- [6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications](https://mlsanity.com/paper/2011.14844/) (2020)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [Communication-Efficient Edge AI: Algorithms and Systems](https://mlsanity.com/paper/2002.09668/) (2020)
- [Towards an Intelligent Edge: Wireless Communication Meets Machine Learning](https://mlsanity.com/paper/1809.00343/) (2018)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [The Conditional Entropy Bottleneck](https://mlsanity.com/paper/2002.05379/) (2020)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [The Information Bottleneck Problem and Its Applications in Machine Learning](https://mlsanity.com/paper/2004.14941/) (2020)
- [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020)
- [Wireless Image Retrieval at the Edge](https://mlsanity.com/paper/2007.10915/) (2020)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Distributed Variational Representation Learning](https://mlsanity.com/paper/1807.04193/) (2018)
- [Learning to Stop While Learning to Predict](https://mlsanity.com/paper/2006.05082/) (2020)
- [Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing](https://mlsanity.com/paper/2011.02422/) (2020)
- [Successive Refinement of Images with Deep Joint Source-Channel Coding](https://mlsanity.com/paper/1903.06333/) (2019)
- [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021)
- [Neural Distributed Source Coding](https://mlsanity.com/paper/2106.02797/) (2021)
- [On Distributed Quantization for Classification](https://mlsanity.com/paper/1911.00216/) (2019)
- [In-Network Learning: Distributed Training and Inference in Networks](https://mlsanity.com/paper/2107.03433/) (2021)
- [On In-network learning. A Comparative Study with Federated and Split Learning](https://mlsanity.com/paper/2104.14929/) (2021)

## Built on by (most cited first, 30 of 52)

- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [WirelessLLM: Empowering Large Language Models Towards Wireless Intelligence](https://mlsanity.com/paper/2405.17053/) (2024)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation](https://mlsanity.com/paper/2209.10382/) (2022)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference](https://mlsanity.com/paper/2503.12926/) (2025)
- [Task-Oriented Communication for Edge Video Analytics](https://mlsanity.com/paper/2211.14049/) (2022)
- [Semantic Information Recovery in Wireless Networks](https://mlsanity.com/paper/2204.13366/) (2022)
- [Semantics-Empowered Communication: A Tutorial-cum-Survey](https://mlsanity.com/paper/2212.08487/) (2022)
- [Tackling Distribution Shifts in Task-Oriented Communication with Information Bottleneck](https://mlsanity.com/paper/2405.09514/) (2024)
- [The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks](https://mlsanity.com/paper/2505.09214/) (2025)
- [Rate-Adaptive Coding Mechanism for Semantic Communications With Multi-Modal Data](https://mlsanity.com/paper/2305.10773/) (2023)
- [Vision Transformer-based Semantic Communications With Importance-Aware Quantization](https://mlsanity.com/paper/2412.06038/) (2024)
- [Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting](https://mlsanity.com/paper/2307.15316/) (2023)
- [Collaborative Edge AI Inference over Cloud-RAN](https://mlsanity.com/paper/2404.06007/) (2024)
- [Semantic Communication for Cooperative Multi-Task Processing over Wireless Networks](https://mlsanity.com/paper/2404.08483/) (2024)
- [Cooperative and Collaborative Multi-Task Semantic Communication for Distributed Sources](https://mlsanity.com/paper/2411.02150/) (2024)
- [Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges](https://mlsanity.com/paper/2411.18199/) (2024)
- [Learn to Communicate with Neural Calibration: Scalability and Generalization](https://mlsanity.com/paper/2110.00272/) (2021)
- [Enabling All In-Edge Deep Learning: A Literature Review](https://mlsanity.com/paper/2204.03326/) (2022)
- [Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge](https://mlsanity.com/paper/2503.13421/) (2025)
- [Task-Oriented Communication Design at Scale](https://mlsanity.com/paper/2305.08481/) (2023)
- [VideoQA-SC: Adaptive Semantic Communication for Video Question Answering](https://mlsanity.com/paper/2406.18538/) (2024)
- [Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems](https://mlsanity.com/paper/2404.13348/) (2024)
- [Task-Oriented Communication for Graph Data: A Graph Information Bottleneck Approach](https://mlsanity.com/paper/2409.02728/) (2024)
- [Importance-Aware Semantic Communication in MIMO-OFDM Systems Using Vision Transformer](https://mlsanity.com/paper/2508.07696/) (2025)
- [Towards Scalable Wireless Federated Learning: Challenges and Solutions](https://mlsanity.com/paper/2310.05076/) (2023)
- [Task-Oriented Edge Networks: Decentralized Learning Over Wireless Fronthaul](https://mlsanity.com/paper/2312.01288/) (2023)
- [GeNet: A Graph Neural Network-based Anti-noise Task-Oriented Semantic Communication Paradigm](https://mlsanity.com/paper/2403.18296/) (2024)
- [Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication with Visual Feature Alignment](https://mlsanity.com/paper/2412.00862/) (2024)

## Abstract (arXiv)

This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage an information bottleneck (IB) principle to extract the task-relevant feature at each edge device and adopt a distributed information bottleneck (DIB) framework to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational approximations to make the optimization problems tractable. To compensate the potential performance loss due to the variational approximations, we also develop a selective retransmission (SR) mechanism to identify the redundancy in the encoded features of multiple edge devices to attain additional communication overhead reduction. Extensive experiments evidence that the proposed task-oriented communication scheme achieves a better rate-relevance tradeoff than baseline methods.