Sylvas schedules valuable devices for better federated continual learning
Sylvas: Synergistic Learning Value based Device Scheduling in Federated Continual Learning
Machine LearningArtificial Intelligence
Summary
Federated continual learning helps many devices work together to improve a shared AI model as data changes over time. The authors present Sylvas, a new way to figure out which devices have the most useful information for updating the model. Sylvas looks at how data changes across places and times and how reliable unlabeled data is. It then chooses the best devices to update the model while keeping communication and computing limits in mind. This method helps build smarter and timely AI systems for networks of devices.
What this means in practice
- •For iot network operators: Use Sylvas to select edge devices that most improve shared AI models under network and computation limits for real-time IoT applications.
- •For autonomous vehicle developers: Schedule edge devices that provide the most valuable data to keep AI models updated in changing traffic and environmental conditions.
Authors
Yuxuan Sun, Yuxuan Bai, Tan Chen, Sheng Zhou, Zhisheng Niu
Abstract
Federated continual learning (FCL) enables shared global models to continuously adapt to distributed and non-stationary data streams, making it important for Internet of Things applications such as intelligent transportation, industrial monitoring, and unmanned systems. Under spatio-temporal data distribution dynamics and label scarcity, a key challenge is how to quantify the contribution of each edge device to global learning performance and schedule the most valuable devices under resource constraints for timely model updating. This article presents Sylvas, a synergistic learning value based device scheduling framework for FCL at the wireless edge. Sylvas evaluates the learning value of distributed data from two perspectives: distributional value, which characterizes the contribution of device data to global model learning from a spatio-temporal distribution perspective, and label value, which captures the quantity and reliability tradeoff of pseudo-labeled data. By integrating these factors into a synergistic learning value metric, Sylvas schedules devices with high learning value while satisfying communication and computation resource constraints. Case studies demonstrate that Sylvas supports timely model adaptation under spatio-temporal distribution dynamics and effectively exploits unlabeled data.