通过识别神经元规律性，分阶段预训练提升钙成像解码效果。
Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining
- 先筛选规律性强的神经元做掩码重建，再微调随机性高的群体
- 在阿灵顿脑图谱数据集上相对基线提升12%~13%性能
- 适合需要稳定扩展模型规模的神经信号解码任务
神经记录中存在由细胞类型、内在回路动态和刺激-响应随机性带来的独特异质性，混合了统计规律性强与高度随机、依赖刺激的神经元。这种异质性使自监督学习难以捕捉可学习的统计规律，导致表征学习不稳定并限制可扩展性。我们提出POYO-CAP（细胞模式感知预训练），一种生物合理的混合预训练策略：首先对通过偏度和峰度识别出的统计规律性强的神经元进行掩码重建与轻量辅助监督训练，随后在更随机的群体上微调。在阿灵顿脑图谱（Allen Brain Observatory）数据集上，该课程学习方法相比从头训练提升12%~13%相对性能，并实现模型规模增长时平稳单调的性能提升；而混合群体训练的基线则出现平台期或不稳定。通过将统计可预测性作为显式数据选择标准，POYO-CAP将神经异质性转化为可扩展的学习优势，提升神经解码鲁棒性。
原文摘要 · Abstract (English)
Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic stimulus-response variability that goes beyond ordinary dataset variability, mixing statistically regular neurons with highly stochastic, stimulus-contingent ones within the same dataset. This heterogeneity poses a challenge for self-supervised learning (SSL) -- learnable statistical regularity -- thereby destabilizing representation learning and limiting reliable scaling. We introduce POYO-CAP (Cell-pattern Aware Pretraining), a biologically grounded hybrid pretraining strategy that first trains with masked reconstruction plus lightweight auxiliary supervision on statistically regular neurons -- identified via skewness and kurtosis -- and then fine-tunes on more stochastic populations. On the Allen Brain Observatory dataset, this curriculum yields 12--13\% relative improvements over from-scratch training and enables smooth, monotonic scaling with model size, whereas baselines trained on mixed populations plateau or destabilize. By making statistical predictability an explicit data-selection criterion, POYO-CAP turns neural heterogeneity into a scalable learning advantage for robust neural decoding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。