A Cyclic Adaptation-Generalization Framework with Uncertainty-Guided Self-Paced Learning for Long-Term Brain-Machine Interfaces

2026-07-27

AI Summary

This study addresses the persistent performance degradation in long-term brain–computer interfaces caused by neural signal drift, particularly under fine-grained subdomain distribution shifts that challenge existing methods. To tackle this issue, the authors propose an Uncertainty-guided Self-Paced Cyclic framework (UnSPC), which uniquely integrates domain adaptation and domain generalization in a cyclic manner. UnSPC employs an uncertainty-guided self-paced pseudo-labeling mechanism to select reliable samples, combined with noise-robust ranking and iterative domain alignment to progressively mitigate both global and subdomain-level drifts. Experiments across multiple neural decoding datasets demonstrate that UnSPC significantly slows performance decay over extended use, offering a novel paradigm toward stable, infrequently recalibrated brain–computer control.

Abstract

Brain-Machine Interfaces (BMIs), which link the brain to external devices, hold great potential in rehabilitation, human performance augmentation, and human-centered robotics. However, invasive BMIs face a critical challenge for long-term deployment due to neural drift, which degrades decoding performance over time and necessitates frequent recalibration. Existing methods designed to mitigate neural drift typically rely on either domain adaptation (DA) or domain generalization (DG) alone and often fail to capture fine-grained distribution shifts across neural subdomains, resulting in limited performance. To overcome these limitations, we propose Uncertainty-guided Self-paced Cycling (UnSPC), a robust framework that synergizes DA and DG for target domain refining under an Uncertainty-guided Self-paced Pseudo-labeling (UnSPL) mechanism. To handle subdomain neural drift across domains, UNSPL is proposed to iteratively mine reliable pseudo-labeled samples with a noise-robust ranking strategy for further fine-tuning. Leveraging these high-quality samples, we introduce a novel Cycling Adaptation and Generalization (CycAG) strategy, which integrates DA and DG within an iterative cycle to progressively mitigate both global and subdomain drift. This cyclic process enables effective alignment to evolving target distributions while preserving robust and transferable representations, thereby mitigating performance degradation under long-term neural drifts. Extensive experiments on multiple neural decoding datasets demonstrate the effectiveness and robustness of UnSPC. To our knowledge, our proposed UnSPC is the first to cyclically integrate DA and DG with pseudo-labeling, paving the way toward stable long-term BMI controls.

Problem

• neural drift
• brain-machine interfaces
• domain adaptation
• domain generalization
• long-term stability

Innovation

• cyclic adaptation-generalization
• uncertainty-guided self-paced learning
• neural drift
• pseudo-labeling
• brain-machine interfaces