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

TL;DR

This paper introduces a personalized federated learning framework with spiking neural networks for brain-computer interface-based immersive communication, enhancing personalization, privacy, and energy efficiency.

Contribution

It develops a novel SNN-enabled PFL model that improves energy efficiency and personalization in BCI-enabled immersive communication systems.

Findings

Achieves the best overall identification accuracy on real brain-signal data.

Reduces inference energy consumption by 6.46 times compared to traditional neural networks.

Effectively handles neurodiverse brain-signal data and preserves privacy.

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.