Spiking Personalized Federated Learning for Brain-Computer Interface-Enabled Immersive Communication

2026-03-23

AI Summary

This work addresses the challenge of personalization in brain–computer interface (BCI)-driven immersive communication, where substantial inter-subject neural variability, sensitivity of brain signals, and stringent terminal energy constraints hinder effective adaptation. To this end, we propose the first framework that integrates spiking neural networks (SNNs) with personalized federated learning (PFL). Leveraging the event-driven sparse computation inherent to SNNs, our approach efficiently models individual brain signals to infer user intent and discomfort states while preserving privacy. Evaluated on real electroencephalography (EEG) datasets, the system achieves state-of-the-art recognition accuracy and reduces inference energy consumption by 6.46× compared to conventional artificial neural networks, thereby effectively balancing personalization, privacy preservation, and energy efficiency.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Privacy
• Humans and AI: Brain-Sensing and Analysis

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This work proposes a novel immersive communication framework that leverages brain-computer interface (BCI) to acquire brain signals for inferring user-centric states (e.g., intention and perception-related discomfort), thereby enabling more personalized and robust immersive adaptation under strong individual variability. Specifically, we develop a personalized federated learning (PFL) model to analyze and process the collected brain signals, which not only accommodates neurodiverse brain-signal data but also prevents the leakage of sensitive brain-signal information. To address the energy bottleneck of continual on-device learning and inference on energy-limited immersive terminals (e.g., head-mounted display), we further embed spiking neural networks (SNNs) into the PFL. By exploiting sparse, event-driven spike computation, the SNN-enabled PFL reduces the computation and energy cost of training and inference while maintaining competitive personalization performance. Experiments on real brain-signal dataset demonstrate that our method achieves the best overall identification accuracy while reducing inference energy by 6.46$\times$ compared with conventional artificial neural network-based personalized baselines.

Problem

• Brain-Computer Interface
• Personalized Federated Learning
• Spiking Neural Networks
• Immersive Communication
• Energy Efficiency

Innovation

• Spiking Neural Networks
• Personalized Federated Learning
• Brain-Computer Interface
• Immersive Communication
• Energy-Efficient Inference