DN-CL: Deep Symbolic Regression against Noise via Contrastive Learning
원문 초록
Noise ubiquitously exists in signals due to numerous factors including physical, electronic, and environmental effects. Traditional methods of symbolic regression, such as genetic programming or deep learning models, aim to find the most fitting expressions for these signals. However, these methods often overlook the noise present in real-world data, leading to reduced fitting accuracy. To tackle this issue, we propose \textit{\textbf{D}eep Symbolic Regression against \textbf{N}oise via \textbf{C}ontrastive \textbf{L}earning (DN-CL)}. DN-CL employs two parameter-sharing encoders to embed data points from various data transformations into feature shields against noise. This model treats noisy data and clean data as different views of the ground-truth mathematical expressions. Distances between these features are minimized, utilizing contrastive learning to distinguish between 'positive' noise-corrected pairs and 'negative' contrasting pairs. Our experiments indicate that DN-CL demonstrates superior performance in handling both noisy and clean data, presenting a promising method of symbolic regression.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Vector Contrastive Learning For Pixel-Wise Pretraining In Medical Vision
Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression
Neural Network-Guided Symbolic Regression for Interpretable Descriptor Discovery in Perovskite Catalysts
DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience
Diffusion-Based Symbolic Regression
Symbolic Foundation Regressor on Complex Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.