Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 9 Oct 2025.
Builds on
27 of 34 references.
References · 27
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2020Exploring Simple Siamese Representation Learningcited by 2,866
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
- 2019Green AIcited by 627
- 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
- 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
- 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
- 2021Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learningcited by 119
15 more
- 2021Towards the Generalization of Contrastive Self-Supervised Learningcited by 99
- 2022Understanding Collapse in Non-Contrastive Siamese Representation Learningcited by 42
- 2022What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?cited by 40
- 2021Federated Contrastive Learning for Decentralized Unlabeled Medical Imagescited by 34
- 2024Relaxed Contrastive Learning for Federated Learningcited by 32
- 2024Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantitycited by 19
- 2022The Cost of Training Machine Learning Models over Distributed Data Sourcescited by 18
- 2021On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signalscited by 14
- 2024Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendationscited by 12
- 2021Dissecting FLOPs along input dimensions for GreenAI cost estimationscited by 10
- 2021ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasetscited by 9
- 2023Quantifying the Variability Collapse of Neural Networkscited by 9
- 2021Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Trainingcited by 6
- 2022Establishing a stronger baseline for lightweight contrastive modelscited by 3
- 2024On Improving the Algorithm-, Model-, and Data- Efficiency of Self-Supervised Learningcited by 1
Built on by
Not cited yet.