Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science(广东省数据科学交叉研究与应用重点实验室);Beijing Normal University-Hong Kong Baptist University United International College(北京师范大学-香港浸会大学联合国际学院)
Yuqian Wu, Hengyi Luo, Raymond S. T. Lee
备注:
15 pages, 2figures, accepted to ICONIP 2024, Paper ID: 1399
Tabular data learning has extensive applications in deep learning but its existing embedding techniques are limited in numerical and categorical features such as the inability to capture complex relationships and engineering. This paper proposes a novel deep embedding framework with leverages lightweight deep neural networks to generate effective feature embeddings for tabular data in machine learning research. For numerical features, a two-step feature expansion and deep transformation technique is used to capture copious semantic information. For categorical features, a unique identification vector for each entity is referred by a compact lookup table with a parameterized deep embedding function to uniform the embedding size dimensions, and transformed into a embedding vector using deep neural network. Experiments are conducted on real-world datasets for performance evaluation.
UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding
University of Electronic Science and Technology of China(电子科学与技术大学);Independent Researcher(独立研究者);University of Science and Technology of China(科学技术大学);Nanyang Technological University(南洋理工大学)
Tabular Learning: Encoding for Entity and Context Embeddings
Institute for Data Applications and Security(数据应用与安全研究院);School of Engineering and Computer Science(工程与计算机科学学院);Bern University of Applied Sciences(伯尔尼应用科学大学)
DANets: Deep Abstract Networks for Tabular Data Classification and Regression
Zhejiang University(浙江大学);Huazhong University of Science and Technology(华中科技大学);University of Notre Dame(圣母大学);Zhejiang University School of Medicine(浙江大学医学院)
Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?
Department of Industrial Engineering, University of Yonsei, Republic of Korea, Seoul(延世大学工业工程系);H. Milton Stewart School of Industrial and Systems Engineering (ISyE), Georgia Institute of Technology, USA, GA(佐治亚理工学院H.米尔顿·斯图尔特工业与系统工程学院)
ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Data
Lane Dept. of Computer Science and Electrical Engineering(兰恩计算机科学与电气工程系);Dept. of Geology & Geography(地质与地理系);West Virginia University(西弗吉尼亚大学);Department of Computer Science and Engineering(计算机科学与工程系);Green University of Bangladesh(孟加拉国绿色大学);Stamford University Bangladesh(班加罗尔斯坦福大学)
Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);The Ohio State University(俄亥俄州立大学);China National Key Laboratory for Novel Software Technology(计算机软件新技术国家重点实验室)
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Faculty of Mathematics and Computer Science, Jagiellonian University(数学与计算机科学学院,杰团大学);Doctoral School of Exact and Natural Sciences, Jagiellonian University(精确与自然科学博士学院,杰团大学)
Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification
Universiti Teknologi Malaysia(马来西亚理工大学);Higher Institute for Science and Technology(高等科学技术学院);Imam Abdulrahman Bin Faisal University(伊玛目阿卜杜拉赫曼·本·费萨尔大学)
Vision-based Deep Learning Analysis of Unordered Biomedical Tabular Datasets via Optimal Spatial Cartography
Department of Radiation Oncology, Stanford University(斯坦福大学放射肿瘤学系);Department of Radiology, Stanford University(斯坦福大学放射学系);Institute for Stem Cell Biology and Regenerative Medicine, Stanford University(斯坦福大学干细胞生物学与再生医学研究所);Stanford Cancer Institute, Stanford University(斯坦福癌症研究所)
Muddling Label Regularization: Deep Learning for Tabular Datasets
Ecole Polytechnique(巴黎综合理工学院);Université Paris Dauphine-PSL(巴黎第九大学-巴黎文理研究大学)
深度学习(DL)被认为是计算机视觉、语音识别和自然语言处理的最新技术。直到最近,人们还普遍认为DL与表格数据的学习任务无关,特别是在集成方法被公认为黄金标准的小样本区域。我们提出了一种新的端到端可微的方法来训练一个标准的FFNN。我们的方法,\textbf{Muddling labels for Regularization}(\texttt{MLR}),通过生成无信息标签和在训练过程中在最后一个隐藏层上应用可微的闭合形式正则化方案来惩罚记忆。\texttt{MLR}在来自UCI数据库和Kaggle的几个数据集上的回归和分类任务中优于经典NN和黄金标准(GBDT,RF),涵盖了大范围的样本量和特征样本比。研究人员和从业者可以将\texttt{MLR}作为现成的\DL{}解决方案单独使用,也可以将其集成到最先进的机器学习管道中。