对比学习在边缘设备上的能耗实测发现，看似高耗的SimCLR反而最省电。
Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
- 对比四种主流对比学习框架在边缘场景下的能耗表现
- 在不同数据量下，SimCLR能耗最低，远低于其他模型
- 适合关注边缘AI能效、低资源部署的研究者和开发者
尽管对比学习（CL）在自监督表征学习中展现出巨大潜力，但其在资源受限设备上的部署仍鲜有研究。传统CL框架训练所需的大量计算带来能耗、数据可用性与内存使用等挑战。我们评估了四种广泛应用的CL框架：SimCLR、MoCo、SimSiam和Barlow Twins，聚焦其在边缘与雾计算环境中的实际可行性，并提出包含能耗分析与少样本训练条件的系统性评测策略。结果表明，尽管普遍认为计算开销大，SimCLR在各类数据条件下均表现出最低能耗。此外，我们还评估了轻量化神经架构与CL框架的组合效果。本研究为在算力有限的边缘/雾环境中部署对比学习提供了资源影响洞察，并指出了未来优化方向。
原文摘要 · Abstract (English)
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training conventional CL frameworks pose a set of challenges, particularly in terms of energy consumption, data availability, and memory usage. We conduct an evaluation of four widely used CL frameworks: SimCLR, MoCo, SimSiam, and Barlow Twins. We focus on the practical feasibility of these CL frameworks for edge and fog deployment, and introduce a systematic benchmarking strategy that includes energy profiling and reduced training data conditions. Our findings reveal that SimCLR, contrary to its perceived computational cost, demonstrates the lowest energy consumption across various data regimes. Finally, we also extend our analysis by evaluating lightweight neural architectures when paired with CL frameworks. Our study aims to provide insights into the resource implications of deploying CL in edge/fog environments with limited processing capabilities and opens several research directions for its future optimization.
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。