Transformer-based model for symbolic regression via joint supervised learning
Authors: Wenqiang Li, Weijun Li, Linjun Sun, Min Wu, Lina Yu, Jingyi Liu, Yanjie Li, Songsong Tian
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The benchmark results show that the proposed method is up to 25% higher with respect to the recovery rate of skeletons than typical transformer-based methods. Moreover, our method outperforms state-of-the-art SR methods based on reinforcement learning and genetic programming in terms of the coefficient of determination (R2). |
| Researcher Affiliation | Academia | 1Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China 2School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China 3School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing, China 4Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | Yes | Source code is available at https://github.com/AILWQ/Joint_Supervised_Learning_for_SR. |
| Open Datasets | Yes | We generate the training set containing approximately 100, 000 unique expression skeletons. For each expression, we re-sample its constant values for 10, 20, 30, 40, and 50 times. ... We evaluate our method and current state-of-the-art approaches on the widely used public benchmarks, i.e., the Nguyen benchmark (Uy et al., 2011), Constant, Keijzer (Keijzer, 2003), R rationals (Krawiec & Pawlak, 2013), AI-Feynman database (Udrescu & Tegmark, 2020) and our SSDNC test set. |
| Dataset Splits | Yes | The validation set contains 1K skeletons that are randomly sampled from the base data set and assigned constants that differ from the training set. |
| Hardware Specification | Yes | More specifically, we train the model using the Adam optimizer (Kingma & Ba, 2014) on 4 NVIDIA V100 GPUs. |
| Software Dependencies | No | The paper mentions software like SymPy and gplearn and optimizers like Adam, but it does not specify version numbers for these or other software dependencies used in their own implementation. |
| Experiment Setup | Yes | More detailed hyperparameters are reported in Appendix 5, which were found empirically and not fine-tuned for maximum performance. ... Table 5: Hyperparameters for our models. |