Adaptive Early Exiting for Collaborative Inference over Noisy Wireless Channels
On the map: Efficient LLM inference and serving → Early exit and edge inference
Abstract (arXiv)
Collaborative inference systems are one of the emerging solutions for deploying deep neural networks (DNNs) at the wireless network edge. Their main idea is to divide a DNN into two parts, where the first is shallow enough to be reliably executed at edge devices of limited computational power, while the second part is executed at an edge server with higher computational capabilities. The main advantage of such systems is that the input of the DNN gets compressed as the subsequent layers of the shallow part extract only the information necessary for the task. As a result, significant communication savings can be achieved compared to transmitting raw input samples. In this work, we study early exiting in the context of collaborative inference, which allows obtaining inference results at the edge device for certain samples, without the need to transmit the partially processed data to the edge server at all, leading to further communication savings. The central part of our system is the transmission-decision (TD) mechanism, which, given the information from the early exit, and the wireless channel conditions, decides whether to keep the early exit prediction or transmit the data to the edge server for further processing. In this paper, we evaluate various TD mechanisms and show experimentally, that for an image classification task over the wireless edge, proper utilization of early exits can provide both performance gains and significant communication savings.
Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving. Builds on 12 of its 19 references that are in the map. First posted on arXiv 29 Nov 2023.
Builds on
12 of 19 references.
Closest ancestors · 1
Same direction, newest first
- 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges8 Mar
Other references · 11
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
- 2014Going Deeper with Convolutionscited by 4,239
- 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 592
- 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
- 2017Adaptive Neural Networks for Efficient Inferencecited by 162
- 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 128
- 2019BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systemscited by 95
- 2020Why should we add early exits to neural networks?cited by 70
- 2019BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Servicescited by 68
- 2020Communicate to Learn at the Edgecited by 28
- 2022A Survey on Collaborative DNN Inference for Edge Intelligencecited by 24
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2022Decentralized Low-Latency Collaborative Inference via Ensembles on the Edge
- 2025DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
- 2026CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon
- 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
- 2022Resource-Constrained Edge AI with Early Exit Prediction
- 2022Distributed Deep Learning Inference Acceleration using Seamless Collaboration in Edge Computing
- 2024Early-Exit meets Model-Distributed Inference at Edge Networks
- 2024Collaborative Inference for Large Models with Task Offloading and Early Exiting