Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control
Not on the map. Why?
Abstract (arXiv)
An intelligent Real-Time Sensing (RTS) system must continuously acquire, update, integrate, and apply knowledge to adapt to real-world dynamics. Managing distributed intelligence in this context requires Federated Continual Learning (FCL). However, effectively capturing the diverse characteristics of RTS data in FCL systems poses significant challenges, including severely impacting computational and communication resources, escalating energy costs, and ultimately degrading overall system performance. To overcome these challenges, we investigate how the data distribution shift from ideal to practical RTS scenarios affects Artificial Intelligence (AI) model performance by leveraging the textitgeneralization gap concept. In this way, we can analyze how sampling time in RTS correlates with the decline in AI performance, computation cost, and communication efficiency. Based on this observation, we develop a novel Sample-driven Control for Federated Continual Learning (SCFL) technique, specifically designed for mobile edge networks with RTS capabilities. In particular, SCFL is an optimization problem that harnesses the sampling process to concurrently minimize the generalization gap and improve overall accuracy while upholding the energy efficiency of the FCL framework. To solve the highly complex and time-varying optimization problem, we introduce a new soft actor-critic algorithm with explicit and implicit constraints (A2C-EI). Our empirical experiments reveal that we can achieve higher efficiency compared to other DRL baselines. Notably, SCFL can significantly reduce energy consumption up to 85% while maintaining FL convergence and timely data transmission.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 11 Oct 2023.
Builds on
34 of 70 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
- 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 674
- 2017Exploring Generalization in Deep Learningcited by 600
- 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
- 2021Gradient Projection Memory for Continual Learningcited by 348
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
- 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
- 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
22 more
- 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
- 2022Federated Class-Incremental Learningcited by 127
- 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 117
- 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
- 2015How much does your data exploration overfit? Controlling bias via information usagecited by 95
- 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
- 2019Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocationcited by 94
- 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
- 2021Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learningcited by 72
- 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
- 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
- 2023Federated Incremental Semantic Segmentationcited by 36
- 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 33
- 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 31
- 2023GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgettingcited by 27
- 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
- 2022HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networkscited by 12
- 2023Complement Sparsification: Low-Overhead Model Pruning for Federated Learningcited by 12
- 2019"Jam Me If You Can'': Defeating Jammer with Deep Dueling Neural Network Architecture and Ambient Backscattering Augmented Communicationscited by 7
- 2020Communication Efficient Federated Learning with Energy Awareness over Wireless Networkscited by 7
- 2022Federated PCA on Grassmann Manifold for Anomaly Detection in IoT Networkscited by 5
- 2022Label driven Knowledge Distillation for Federated Learning with non-IID Datacited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.