ReConTab：面向表格数据的正则化对比表示学习
ReConTab: Regularized Contrastive Representation Learning for Tabular Data
AI总结：
针对表格数据特征工程依赖人工的问题，提出结合正则化与对比学习的深度表示学习框架ReConTab，可生成低维嵌入，提升多类传统方法性能。
摘要：
表示学习是跨多个领域的关键机器学习技术之一。通过获取高质量特征，预训练嵌入可显著降低输入空间的冗余度，为分类、回归或检测等下游模式识别任务带来增益。但在表格数据领域，特征工程与特征选择仍高度依赖人工干预，不仅流程耗时，还要求从业者具备领域专业知识。针对这一挑战，我们提出ReConTab——一种结合正则化对比学习的深度自动表示学习框架。ReConTab对各类建模任务均无偏向，它基于模型输入的相同原始特征构建非对称自编码器，生成低维表征嵌入。具体而言，该框架采用正则化技术进行原始特征选择，同时利用对比学习为下游任务提炼最相关的信息。在大量真实世界数据集上开展的实验证实，该框架能够带来显著且稳健的性能提升。此外，我们通过实验证明，预训练嵌入可作为易适配的特征无缝集成，提升XGBoost、随机森林（Random Forest）等多种传统方法的性能。
英文摘要：
Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting downstream pattern recognition tasks such as classification, regression, or detection. Nonetheless, in the domain of tabular data, feature engineering and selection still heavily rely on manual intervention, leading to time-consuming processes and necessitating domain expertise. In response to this challenge, we introduce ReConTab, a deep automatic representation learning framework with regularized contrastive learning. Agnostic to any type of modeling task, ReConTab constructs an asymmetric autoencoder based on the same raw features from model inputs, producing low-dimensional representative embeddings. Specifically, regularization techniques are applied for raw feature selection. Meanwhile, ReConTab leverages contrastive learning to distill the most pertinent information for downstream tasks. Experiments conducted on extensive real-world datasets substantiate the framework's capacity to yield substantial and robust performance improvements. Furthermore, we empirically demonstrate that pre-trained embeddings can seamlessly integrate as easily adaptable features, enhancing the performance of various traditional methods such as XGBoost and Random Forest.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
