Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data

TL;DR

The Taylor-Sensus Network (TSNet) introduces a novel approach for modeling complex noise in scientific data using Taylor series expansion, improving uncertainty estimation and noise resistance in machine learning applications.

Contribution

TSNet innovatively models heteroscedastic noise with a deep Taylor block and combines aleatoric and epistemic uncertainties for enhanced scientific data analysis.

Findings

TSNet outperforms existing methods in uncertainty estimation accuracy.

TSNet effectively models complex noise in structured scientific data.

The approach is validated through experiments demonstrating superior noise resistance.

Abstract

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".