Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems

2019-10-01 · Yoshitomo Matsubara, Sabur Baidya, Davide Callegaro, Marco Levorato, Sameer Singh

Offloading the execution of complex Deep Neural Networks (DNNs) models to compute-capable devices at the network edge, that is, edge servers, can significantly reduce capture-to-output delay. However, the communication link between the mobile devices and edge servers can become the bottleneck when channel conditions are poor. We propose a framework to split DNNs for image processing and minimize capture-to-output delay in a wide range of network conditions and computing parameters. The core idea is to split the DNN models into head and tail models, where the two sections are deployed at the mobile device and edge server, respectively. Different from prior literature presenting DNN splitting frameworks, we distill the architecture of the head DNN to reduce its computational complexity and introduce a bottleneck, thus minimizing processing load at the mobile device as well as the amount of wirelessly transferred data. Our results show 98% reduction in used bandwidth and 85% in computation load compared to straightforward splitting.

📄 PDF Abstract BibTeX

Code (2)

yoshitomo-matsubara/head-network-distillation 공식 구현 pytorch

yoshitomo-matsubara/torchdistill pytorch

Tasks

Edge-computingImage Classification Knowledge Distillation Model Compression Neural Network Compression

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Edge-assisted U-Shaped Split Federated Learning with Privacy-preserving for Internet of Things

2023-11-08 · Hengliang Tang, Zihang Zhao, Detian Liu, Yang Cao 외

In the realm of the Internet of Things (IoT), deploying deep learning models to process data generated or collected by IoT devices is a critical challenge. However, direct data transmission can cause network congestion a…

Federated Learning Privacy Preserving

Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning

2020-08-21 · Yiming Li, Jiawang Bai, Jiawei Li, Xue Yang 외

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distillation based decision trees extension, dub…

BIG-bench Machine Learning Knowledge Distillation

Completion Time Minimization of Fog-RAN-Assisted Federated Learning With Rate-Splitting Transmission

2022-06-03 · Seok-Hwan Park, Hoon Lee

This work studies federated learning (FL) over a fog radio access network, in which multiple internet-of-things (IoT) devices cooperatively learn a shared machine learning model by communicating with a cloud server (CS) …

Federated Learning Quantization

Splitwise: Collaborative Edge-Cloud Inference for LLMs via Lyapunov-Assisted DRL

2025-12-29 · Abolfazl Younesi, Abbas Shabrang Maryan, Elyas Oustad, Zahra Najafabadi Samani 외 arxiv

Deploying large language models (LLMs) on edge devices is challenging due to their limited memory and power resources. Cloud-only inference reduces device burden but introduces high latency and cost. Static edge-cloud pa…

Reinforcement Learning

Fit CATE Once: Model-Assisted Randomization Tests Without Sample Splitting

2026-05-09 · Fangnan Zheng, Yao Zhang arxiv

Randomization tests and flexible treatment-effect models offer complementary strengths for analyzing data from randomized panel experiments: the former provide valid inference under the known assignment mechanism, while …