EdgeOL: Efficient in-situ Online Learning on Edge Devices

• URL: http://arxiv.org/abs/2401.16694v6
• Date: Fri, 16 May 2025 12:48:12 GMT
• Title: EdgeOL: Efficient in-situ Online Learning on Edge Devices
• Authors: Sheng Li, Geng Yuan, Yue Dai, Tianyu Wang, Yawen Wu, Alex K. Jones, Jingtong Hu, Tony, Geng, Yanzhi Wang, Bo Yuan, Yufei Ding, Xulong Tang,
• Abstract summary: We propose EdgeOL, an edge online learning framework that optimize inference accuracy, fine-tuning execution time, and energy efficiency.<n> Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy.
• Score: 51.86178757050963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy

Related papers

• MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration [8.43012094714496]
  This paper presents a unified framework for codifying and automating optimization strategies to deploy deep neural networks (DNNs) on resource-constrained hardware.<n>Our novel approach addresses two key issues: (i)encoding custom optimization strategies and (ii)enabling cross-stage optimization search.
  arXiv  Detail & Related papers  (2025-02-09T11:02:06Z)
• Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity [39.483346492111515]
  Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements when accelerated by compatible hardware platforms. We find that highly sparse linear RNNs consistently achieve better efficiency-performance trade-offs than dense baselines.
  arXiv  Detail & Related papers  (2025-02-03T13:09:21Z)
• The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit [46.37267466656765]
  This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture. Our experiments demonstrate how this architecture effectively decreases time without sacrificing the accuracy needed for reliable recommendation delivery.
  arXiv  Detail & Related papers  (2025-01-04T03:26:46Z)
• EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge [2.8946323553477704]
  We propose EdgeRL framework that seeks to strike balance by using an Advantage Actor-Critic (A2C) Reinforcement Learning (RL) approach. We evaluate the benefits of EdgeRL framework in terms of end device energy savings, inference accuracy improvement, and end-to-end inference latency reduction.
  arXiv  Detail & Related papers  (2024-10-16T04:31:39Z)
• Neural Horizon Model Predictive Control -- Increasing Computational Efficiency with Neural Networks [0.0]
  We propose a proposed machine-learning supported approach to model predictive control. We propose approximating part of the problem horizon, while maintaining safety guarantees. The proposed MPC scheme can be applied to a wide range of applications, including those requiring a rapid control response.
  arXiv  Detail & Related papers  (2024-08-19T08:13:37Z)
• EON-1: A Brain-Inspired Processor for Near-Sensor Extreme Edge Online Feature Extraction [32.343120409334475]
  EON-1 is a brain-inspired processor for near-sensor extreme edge online feature extraction. We report results of only 1% energy overhead for learning, by far the lowest overhead when compared to other SoTA solutions.
  arXiv  Detail & Related papers  (2024-06-25T05:23:41Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments [4.343246899774834]
  Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. We propose an automated augmentation flow that focuses on converting an existing model into an EENN. Our framework constructs the EENN architecture, maps its subgraphs to the hardware targets, and configures its decision mechanism.
  arXiv  Detail & Related papers  (2024-03-12T08:27:53Z)
• Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing [11.403989519949173]
  This work focuses on the timeliness of computational-intensive updates, measured by Age-ofInformation (AoI) We study how to jointly optimize the task updating and offloading policies for AoI with fractional form. Experimental results show that our proposed algorithms reduce the average AoI by up to 57.6% compared with several non-fractional benchmarks.
  arXiv  Detail & Related papers  (2023-12-16T11:13:40Z)
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization [71.87335804334616]
  Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. The training process of Large Language Models (LLMs) generally incurs the update of significant parameters. This paper proposes an efficient partial prompt tuning approach to improve performance and efficiency simultaneously.
  arXiv  Detail & Related papers  (2023-10-23T16:37:59Z)
• Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning [55.08287089554127]
  Open Radio Access Network systems, with their base stations (vBSs), offer operators the benefits of increased flexibility, reduced costs, vendor diversity, and interoperability.<n>We propose an online learning algorithm that balances the effective throughput and vBS energy consumption, even under unforeseeable and "challenging'' environments.<n>We prove the proposed solutions achieve sub-linear regret, providing zero average optimality gap even in challenging environments.
  arXiv  Detail & Related papers  (2023-09-04T17:30:21Z)
• Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks [3.6076391721440633]
  Collaborative end-edge-cloud computing for deep learning provides a range of performance and efficiency. We propose a reinforcement-learning-based computation offloading solution that learns optimal offloading policy. Our solution provides 35% speedup in the average response time compared to the state-of-the-art with less than 0.9% accuracy reduction.
  arXiv  Detail & Related papers  (2022-02-21T21:41:29Z)
• NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models [90.6485663020735]
  Fine-tuning from pre-trained ImageNet models has been a simple, effective, and popular approach for various computer vision tasks. We propose a joint Neural Architecture Search and Online Adaption framework named NASOA towards a faster task-oriented fine-tuning.
  arXiv  Detail & Related papers  (2021-08-07T12:03:14Z)
• Active Learning for Deep Neural Networks on Edge Devices [0.0]
  This paper formalizes a practical active learning problem for neural networks on edge devices. We propose a general task-agnostic framework to tackle this problem, which reduces it to a stream submodular property. We evaluate our approach on both classification and object detection tasks in a practical setting to simulate a real-life scenario.
  arXiv  Detail & Related papers  (2021-06-21T03:55:33Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration [20.92912642901645]
  We propose a Saliency-Adaptive Sparsity Learning (SASL) approach for further optimization. Our method can reduce 49.7% FLOPs of ResNet-50 with very negligible 0.39% top-1 and 0.05% top-5 accuracy degradation.
  arXiv  Detail & Related papers  (2020-03-12T16:49:37Z)
• Self-Directed Online Machine Learning for Topology Optimization [58.920693413667216]
  Self-directed Online Learning Optimization integrates Deep Neural Network (DNN) with Finite Element Method (FEM) calculations. Our algorithm was tested by four types of problems including compliance minimization, fluid-structure optimization, heat transfer enhancement and truss optimization. It reduced the computational time by 2 5 orders of magnitude compared with directly using methods, and outperformed all state-of-the-art algorithms tested in our experiments.
  arXiv  Detail & Related papers  (2020-02-04T20:00:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.