用泰勒展开建模科学数据中的复杂噪声，提升不确定性估计精度。
Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data
- 通过泰勒展开构建深层噪声感知模块，显式建模异方差噪声。
- 在多个科学数据集上超越主流方法，噪声鲁棒性显著增强。
- 适合需高可靠性预测的科研场景，如生物医学与物理模拟。
不确定性估计在科学数据的机器学习中至关重要。现有方法多关注模型内在不确定性，忽视数据中显式的噪声建模。此外，噪声估计通常依赖时间或空间依赖性，在结构化科学数据中样本间常缺乏此类关系，导致应用受限。为此，我们提出泰勒-桑森网络（TSNet），创新性地采用泰勒级数展开建模复杂、异方差噪声，并设计深度泰勒块以感知噪声分布。TSNet包含噪声感知对比学习模块和数据密度感知模块，分别用于建模随机性（aleatoric）与认知性（epistemic）不确定性。同时引入不确定性组合算子融合两类不确定性，并使用新型异方差均方误差损失进行训练。实验表明，TSNet在多个科学数据集上优于主流及前沿方法，展现出优异的噪声鲁棒性与科学应用潜力。代码将开源，助力‘AI for Science’社区发展。
原文摘要 · Abstract (English)
Uncertainty estimation is crucial in scientific data for machine learning. Current uncertainty estimation methods mainly focus on the model's inherent uncertainty, while neglecting the explicit modeling of noise in the data. Furthermore, noise estimation methods typically rely on temporal or spatial dependencies, which can pose a significant challenge in structured scientific data where such dependencies among samples are often absent. To address these challenges in scientific research, we propose the Taylor-Sensus Network (TSNet). TSNet innovatively uses a Taylor series expansion to model complex, heteroscedastic noise and proposes a deep Taylor block for aware noise distribution. TSNet includes a noise-aware contrastive learning module and a data density perception module for aleatoric and epistemic uncertainty. Additionally, an uncertainty combination operator is used to integrate these uncertainties, and the network is trained using a novel heteroscedastic mean square error loss. TSNet demonstrates superior performance over mainstream and state-of-the-art methods in experiments, highlighting its potential in scientific research and noise resistance. It will be open-source to facilitate the community of "AI for Science".
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。