用持续对比学习提升表格数据在分布外情况下的泛化能力
Continual Contrastive Learning on Tabular Data with Out of Distribution
- 将对比学习与持续学习结合，构建编码器-解码器-学习头架构
- 在8个数据集上超越14种基线模型，对分布偏移鲁棒性更强
- 适合需要长期适应新数据的工业级表格数据分析场景
分布外（OOD）预测仍是机器学习中的重大挑战，尤其在表格数据中，传统方法常难以泛化到训练分布之外。本文提出表格持续对比学习（TCCL），一种针对表格数据处理中OOD问题的新框架。TCCL融合对比学习与持续学习机制，采用三组件架构：编码器用于数据变换，解码器用于表征学习，学习头用于任务输出。我们在8个多样化的表格数据集上，与14种基线模型（包括前沿深度学习方法和梯度提升决策树）进行对比评估。实验结果表明，TCCL在分类与回归任务中均能持续优于现有方法，尤其在应对分布偏移时表现突出。这些发现表明，TCCL在表格数据的分布外场景下具有显著进步。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) prediction remains a significant challenge in machine learning, particularly for tabular data where traditional methods often fail to generalize beyond their training distribution. This paper introduces Tabular Continual Contrastive Learning (TCCL), a novel framework designed to address OOD challenges in tabular data processing. TCCL integrates contrastive learning principles with continual learning mechanisms, featuring a three-component architecture: an Encoder for data transformation, a Decoder for representation learning, and a Learner Head. We evaluate TCCL against 14 baseline models, including state-of-the-art deep learning approaches and gradient-boosted decision trees (GBDT), across eight diverse tabular datasets. Our experimental results demonstrate that TCCL consistently outperforms existing methods in both classification and regression tasks on OOD data, with particular strength in handling distribution shifts. These findings suggest that TCCL represents a significant advancement in handling OOD scenarios for tabular data.
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。