针对边缘设备优化自监督学习，显著降低能耗与资源消耗。
Self-Supervised Learning at the Edge: The Cost of Labeling
- 设计适配边缘计算的自监督学习策略，平衡性能与资源消耗。
- 实验表明资源消耗最高可降低4倍，性能仍具竞争力。
- 分析标注数据的能耗，提出半监督方法减少训练总能耗。
对比学习（CL）近年来作为传统监督学习的替代方案，能够从无结构、未标注数据中提取丰富表示。然而，CL及更广泛的自监督学习（SSL）方法通常需要大量数据和计算资源，对资源受限的边缘设备部署构成挑战。本文研究了在边缘环境下使用SSL技术的可行性与效率，重点分析模型性能与能效之间的权衡。特别地，我们评估了不同SSL方法在计算、数据和能源预算有限条件下的适应能力，考察其在资源受限场景下学习鲁棒表示的有效性。此外，还考虑了数据标注带来的能耗，并评估半监督学习在降低训练CL模型总能耗方面的潜力。通过大量实验，结果表明，经过定制的SSL策略可在保持优异性能的同时，将资源消耗最多降低4倍，凸显其在边缘高效学习中的巨大潜力。
原文摘要 · Abstract (English)
Contrastive learning (CL) has recently emerged as an alternative to traditional supervised machine learning solutions by enabling rich representations from unstructured and unlabeled data. However, CL and, more broadly, self-supervised learning (SSL) methods often demand a large amount of data and computational resources, posing challenges for deployment on resource-constrained edge devices. In this work, we explore the feasibility and efficiency of SSL techniques for edge-based learning, focusing on trade-offs between model performance and energy efficiency. In particular, we analyze how different SSL techniques adapt to limited computational, data, and energy budgets, evaluating their effectiveness in learning robust representations under resource-constrained settings. Moreover, we also consider the energy costs involved in labeling data and assess how semi-supervised learning may assist in reducing the overall energy consumed to train CL models. Through extensive experiments, we demonstrate that tailored SSL strategies can achieve competitive performance while reducing resource consumption by up to 4X, underscoring their potential for energy-efficient learning at the edge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。