# BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems arXiv: https://arxiv.org/abs/1910.14315 ยท HTML: https://mlsanity.com/paper/1910.14315/ ## Key facts - Cited by 95 papers in the map (data through 14 Oct 2026). - First posted on arXiv 31 Oct 2019. ## Built on by (most cited first, 30 of 95) - [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021) - [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021) - [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021) - [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021) - [Task-Oriented Communication for Multi-Device Cooperative Edge Inference](https://mlsanity.com/paper/2109.00172/) (2021) - [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025) - [Supervised Compression for Resource-Constrained Edge Computing Systems](https://mlsanity.com/paper/2108.11898/) (2021) - [Robust Information Bottleneck for Task-Oriented Communication with Digital Modulation](https://mlsanity.com/paper/2209.10382/) (2022) - [BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing](https://mlsanity.com/paper/2201.02693/) (2022) - [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023) - [Collaborative Intelligence: Challenges and Opportunities](https://mlsanity.com/paper/2102.06841/) (2021) - [Optimal Model Placement and Online Model Splitting for Device-Edge Co-Inference](https://mlsanity.com/paper/2105.13618/) (2021) - [Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference](https://mlsanity.com/paper/2503.12926/) (2025) - [Reinforcement Learning-powered Semantic Communication via Semantic Similarity](https://mlsanity.com/paper/2108.12121/) (2021) - [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022) - [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021) - [SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems](https://mlsanity.com/paper/2204.04705/) (2022) - [Task-Oriented Communication for Edge Video Analytics](https://mlsanity.com/paper/2211.14049/) (2022) - [Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization](https://mlsanity.com/paper/2305.13553/) (2023) - [SplitEE: Early Exit in Deep Neural Networks with Split Computing](https://mlsanity.com/paper/2309.09195/) (2023) - [Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning](https://mlsanity.com/paper/2205.11854/) (2022) - [FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing](https://mlsanity.com/paper/2302.10681/) (2023) - [SplitPlace: AI Augmented Splitting and Placement of Large-Scale Neural Networks in Mobile Edge Environments](https://mlsanity.com/paper/2205.10635/) (2022) - [Resource-Constrained Edge AI with Early Exit Prediction](https://mlsanity.com/paper/2206.07269/) (2022) - [SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization](https://mlsanity.com/paper/2410.10759/) (2024) - [I-SplitEE: Image classification in Split Computing DNNs with Early Exits](https://mlsanity.com/paper/2401.10541/) (2024) - [C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning](https://mlsanity.com/paper/2207.12397/) (2022) - [Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency](https://mlsanity.com/paper/2311.05739/) (2023) - [Communication-oriented Model Fine-tuning for Packet-loss Resilient Distributed Inference under Highly Lossy IoT Networks](https://mlsanity.com/paper/2112.09407/) (2021) - [I-SPLIT: Deep Network Interpretability for Split Computing](https://mlsanity.com/paper/2209.11607/) (2022) ## Abstract (arXiv) The emergence of various intelligent mobile applications demands the deployment of powerful deep learning models at resource-constrained mobile devices. The device-edge co-inference framework provides a promising solution by splitting a neural network at a mobile device and an edge computing server. In order to balance the on-device computation and the communication overhead, the splitting point needs to be carefully picked, while the intermediate feature needs to be compressed before transmission. Existing studies decoupled the design of model splitting, feature compression, and communication, which may lead to excessive resource consumption of the mobile device. In this paper, we introduce an end-to-end architecture, named BottleNet++, that consists of an encoder, a non-trainable channel layer, and a decoder for more efficient feature compression and transmission. The encoder and decoder essentially implement joint source-channel coding via convolutional neural networks (CNNs), while explicitly considering the effect of channel noise. By exploiting the strong sparsity and the fault-tolerant property of the intermediate feature in a deep neural network (DNN), BottleNet++ achieves a much higher compression ratio than existing methods. Furthermore, by providing the channel condition to the encoder as an input, our method enjoys a strong generalization ability in different channel conditions. Compared with merely transmitting intermediate data without feature compression, BottleNet++ achieves up to 64x bandwidth reduction over the additive white Gaussian noise channel and up to 256x bit compression ratio in the binary erasure channel, with less than 2% reduction in accuracy. With a higher compression ratio, BottleNet++ enables splitting a DNN at earlier layers, which leads to up to 3x reduction in on-device computation compared with other compression methods.