GeoRVQ：面向残差令牌预测的生理信号解码器感知几何
GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals
- University of Twente（特文特大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GeoRVQ提出解码器感知的几何目标用于生理信号残差令牌预测，通过粗到细掩码建模提升波形和事件保留，在多个数据集上显著改善解码距离和R峰F1。
AI中文摘要：
残差向量量化（RVQ）将生理波形转换为紧凑的令牌序列，但传统的掩码建模将每个错误令牌视为同等代价。我们提出GeoRVQ，一种从粗到细的掩码令牌模型，其目标函数反映冻结波形解码器的局部响应。解码器引发的代价定义了几何感知的软目标和期望失真，而量化器因果预测则遵循从粗到细的残差依赖关系。在MIMIC-IV Waveform、VitalDB和CODE-15%的描述性汇总中，在匹配的模型和训练条件下，GeoRVQ将精确令牌准确率从$.133\pm.004$提高到$.143\pm.003$，将解码距离从$.606\pm.006$降低到$.393\pm.007$，并将R峰F1分数从$.784\pm.004$提高到$.837\pm.008$。在45个保留的代码替换中，解码器引发的代价与实现解码代价的Spearman相关系数为$.85$，而欧几里得码字距离的相关系数为$.54$。这些结果表明，解码器感知的目标可以在不需要大幅提高精确令牌准确率的情况下改善波形和事件的保留。
英文摘要：
Residual vector quantization (RVQ) turns physiological waveforms into compact token sequences, but conventional masked modeling treats every incorrect token as equally costly. We propose GeoRVQ, a coarse-to-fine masked token model whose objective reflects the local response of a frozen waveform decoder. Decoder-induced costs define geometry-aware soft targets and expected distortion, while quantizer-causal prediction follows residual dependencies from coarse to fine levels. In a descriptive aggregate over MIMIC-IV Waveform, VitalDB, and CODE-15\%, GeoRVQ increases exact token accuracy from $.133\pm.004$ to $.143\pm.003$, reduces decoded distance from $.606\pm.006$ to $.393\pm.007$, and increases R-peak F1 from $.784\pm.004$ to $.837\pm.008$ under matched model and training conditions. Across 45 held-out code substitutions, decoder-induced cost has a Spearman correlation of $.85$ with realized decoded cost, compared with $.54$ for Euclidean codeword distance. These results indicate that decoder-aware objectives can improve waveform and event preservation without requiring a large increase in exact token accuracy.
