Summary of Dn-cl: Deep Symbolic Regression Against Noise Via Contrastive Learning, by Jingyi Liu et al.
DN-CL: Deep Symbolic Regression against Noise via Contrastive Learning
by Jingyi Liu, Yanjie Li, Lina Yu, Min Wu, Weijun Li, Wenqiang Li, Meilan Hao, Yusong Deng, Shu Wei
First submitted to arxiv on: 21 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to symbolic regression called Deep Symbolic Regression against Noise via Contrastive Learning (DN-CL). Traditional methods for finding mathematical expressions often overlook noise present in real-world data, leading to reduced accuracy. DN-CL employs two parameter-sharing encoders to embed data points from various transformations into feature shields against noise. The model treats noisy and clean data as different views of the ground-truth expressions and uses contrastive learning to distinguish between positive and negative pairs. Experimental results show that DN-CL outperforms existing methods in handling both noisy and clean data, making it a promising method for symbolic regression. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding mathematical formulas that fit real-world data, but also account for noise that can affect the data. Noise can come from many sources like physical or environmental effects. The researchers propose a new way to do this called DN-CL. It uses special “encoders” to help remove the noise and find the right formulas. They tested their method with different types of data and found it worked better than other approaches. This could be useful for things like predicting stock prices or analyzing medical data. |
Keywords
» Artificial intelligence » Regression
