Cross-Domain Continual Learning for Edge Intelligence in Wireless ISAC Networks

2025-02-18

AI Summary

In wireless Integrated Sensing and Communication (ISAC) networks, edge devices (EDs) face significant challenges in cross-domain generalization and catastrophic forgetting when performing user activity sensing based on channel state information (CSI). To address these issues under stringent resource constraints, this paper proposes EdgeCL—a novel continual learning framework that uniquely integrates a sequence-robust discriminator (built upon Transformer architecture) with a core-set knowledge distillation mechanism. EdgeCL enhances robustness via robustness-aware optimization and enables adaptive core-set sampling to simultaneously preserve cross-user-domain generalization capability and substantially mitigate forgetting. Experimental results demonstrate that EdgeCL achieves an 89% cumulative accuracy with only 3% additional memory overhead, reducing forgetting by 79% compared to baseline methods. This work establishes a scalable, low-overhead paradigm for cross-domain continual sensing in ISAC-enabled edge intelligence.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

In wireless networks with integrated sensing and communications (ISAC), edge intelligence (EI) is expected to be developed at edge devices (ED) for sensing user activities based on channel state information (CSI). However, due to the CSI being highly specific to users' characteristics, the CSI-activity relationship is notoriously domain dependent, essentially demanding EI to learn sufficient datasets from various domains in order to gain cross-domain sensing capability. This poses a crucial challenge owing to the EDs' limited resources, for which storing datasets across all domains will be a significant burden. In this paper, we propose the EdgeCL framework, enabling the EI to continually learn-then-discard each incoming dataset, while remaining resilient to catastrophic forgetting. We design a transformer-based discriminator for handling sequences of noisy and nonequispaced CSI samples. Besides, we propose a distilled core-set based knowledge retention method with robustness-enhanced optimization to train the discriminator, preserving its performance for previous domains while preventing future forgetting. Experimental evaluations show that EdgeCL achieves 89% of performance compared to cumulative training while consuming only 3% of its memory, mitigating forgetting by 79%.

Problem

• Cross-domain continual learning
• Edge intelligence in ISAC networks
• Mitigating catastrophic forgetting

Innovation

• Cross-domain continual learning
• Transformer-based discriminator
• Distilled core-set knowledge retention