BiTimeCrossNet: Time-Aware Self-Supervised Learning for Pediatric Sleep
This work addresses pediatric sleep analysis, offering an incremental improvement by adding time-awareness to existing self-supervised methods for better generalization in sleep staging and event detection.
The paper tackled the problem of analyzing long physiological recordings like overnight sleep studies by proposing BiTimeCrossNet (BTCNet), a multimodal self-supervised learning framework that incorporates time-aware information and cross-attention between signals, resulting in consistent performance gains over non-time-aware variants and strong results on respiration-related tasks across six downstream tasks.
We present BiTimeCrossNet (BTCNet), a multimodal self-supervised learning framework for long physiological recordings such as overnight sleep studies. While many existing approaches train on short segments treated as independent samples, BTCNet incorporates information about when each segment occurs within its parent recording, for example within a sleep session. BTCNet further learns pairwise interactions between physiological signals via cross-attention, without requiring task labels or sequence-level supervision. We evaluate BTCNet on pediatric sleep data across six downstream tasks, including sleep staging, arousal detection, and respiratory event detection. Under frozen-backbone linear probing, BTCNet consistently outperforms an otherwise identical non-time-aware variant, with gains that generalize to an independent pediatric dataset. Compared to existing multimodal self-supervised sleep models, BTCNet achieves strong performance, particularly on respiration-related tasks.