用53%的验证损失改进，让小数据下的符号回归更稳定。
Evaluating K-Fold Cross Validation for Transformer Based Symbolic Regression Models
- 将15,000个数据点分k折训练，交替验证提升泛化能力
- 验证损失相对降低53.31%，输出更一致
- 适合算力有限时做符号回归研究
符号回归仍是NP难问题，尽管人工智能模型已有广泛研究。基于Transformer的符号回归模型在小数据下表现不佳。本文提出对仅含15,000个数据点（原为500,000）的模型应用k折交叉验证，将训练数据划分为多个子集，轮流在部分数据上训练、另一部分上验证。目标是评估模型泛化能力，缓解小数据下的过拟合。结果表明，该方法使验证损失相对下降53.31%，显著提升模型输出一致性和泛化性能，有望在资源受限环境下实现更高效、可及的符号回归。
原文摘要 · Abstract (English)
Symbolic Regression remains an NP-Hard problem, with extensive research focusing on AI models for this task. Transformer models have shown promise in Symbolic Regression, but performance suffers with smaller datasets. We propose applying k-fold cross-validation to a transformer-based symbolic regression model trained on a significantly reduced dataset (15,000 data points, down from 500,000). This technique partitions the training data into multiple subsets (folds), iteratively training on some while validating on others. Our aim is to provide an estimate of model generalization and mitigate overfitting issues associated with smaller datasets. Results show that this process improves the model's output consistency and generalization by a relative improvement in validation loss of 53.31%. Potentially enabling more efficient and accessible symbolic regression in resource-constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。