Taylor-Sensus Network:拥抱噪声以揭示科学数据的不确定性
Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data
AI总结:
针对科学数据不确定性估计忽略数据噪声建模、噪声估计难适配无时空依赖结构化数据的问题,提出TSNet,用泰勒展开建模异方差噪声,结合多模块与新损失函数,性能优于现有方法,将开源助力AI for Science。
摘要:
不确定性估计在科学数据的机器学习应用中至关重要。当前的不确定性估计方法主要关注模型的固有不确定性,却忽略了对数据中噪声的显式建模。此外,噪声估计方法通常依赖时间或空间依赖性,这在样本间往往缺乏此类依赖性的结构化科学数据中会构成重大挑战。为应对科研领域的这些挑战,我们提出了Taylor-Sensus Network(TSNet,泰勒感知网络)。TSNet创新性地采用泰勒级数展开来建模复杂的异方差噪声,并提出深度泰勒模块以感知噪声分布。TSNet包含一个噪声感知对比学习模块和一个数据密度感知模块,分别用于处理偶然不确定性和认知不确定性。此外,该网络使用不确定性组合算子整合这些不确定性,并通过一种新型异方差均方误差损失进行训练。实验表明,TSNet的性能优于主流方法及当前最优(SOTA)方法,凸显了其在科研领域和抗噪声方面的潜力。该网络将开源,以推动“AI for Science(人工智能赋能科学)”社区的发展。
英文摘要:
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".
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。