mlsanityData to 7 Oct 2026

An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic

arXiv 2201.02968 ↗First posted 9 Jan 2022cs.LG cs.AI cs.NIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, the applications of deep neural network (DNN) have been very prominent in many fields such as computer vision (CV) and natural language processing (NLP) due to its superior feature extraction performance. However, the high-dimension parameter model and large-scale mathematical calculation restrict the execution efficiency, especially for Internet of Things (IoT) devices. Different from the previous cloud/edge-only pattern that brings huge pressure for uplink communication and device-only fashion that undertakes unaffordable calculation strength, we highlight the collaborative computation between the device and edge for DNN models, which can achieve a good balance between the communication load and execution accuracy. Specifically, a systematic on-demand co-inference framework is proposed to exploit the multi-branch structure, in which the pre-trained Alexnet is right-sized through early-exit and partitioned at an intermediate DNN layer. The integer quantization is enforced to further compress transmission bits. As a result, we establish a new Deep Reinforcement Learning (DRL) optimizer-Soft Actor Critic for discrete (SAC-d), which generates the exit point, partition point, and compressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an optimizer can well adapt to the complex environment like dynamic wireless channel and arbitrary CPU processing, and is capable of supporting the 5G URLLC. Real-world experiment on Raspberry Pi 4 and PC shows the outperformance of the proposed solution.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 18 references that are in the map. First posted on arXiv 9 Jan 2022.

Builds on

9 of 18 references.

References · 9

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  4. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  5. 2019Soft Actor-Critic for Discrete Action Settingscited by 161
  6. 2018Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergycited by 50
  7. 2018JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Executioncited by 38
  8. 2018Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platformscited by 35
  9. 2018Joint Communication, Computation, Caching, and Control in Big Data Multi-access Edge Computingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Communication-Computation Efficient Device-Edge Co-Inference via AutoML
  2. 2026EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
  3. 2023Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
  4. 2026CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon
  5. 2022Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing
  6. 2023Sustainable Edge Intelligence Through Energy-Aware Early Exiting
  7. 2022Resource-Constrained Edge AI with Early Exit Prediction
  8. 2022Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing