SwitchTab: Switched Autoencoders Are Effective Tabular Learners
This addresses the problem of less pronounced dependencies in tabular data for researchers and practitioners in machine learning, offering a novel method that is incremental in improving self-supervised techniques for this domain.
The paper tackled the challenge of applying self-supervised representation learning to tabular data by introducing SwitchTab, a method that captures latent dependencies through an asymmetric encoder-decoder framework, resulting in superior performance in end-to-end prediction tasks and enhanced features for traditional classifiers.
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to tabular data is challenging due to the less pronounced dependencies among data samples. In this paper, we address this limitation by introducing SwitchTab, a novel self-supervised method specifically designed to capture latent dependencies in tabular data. SwitchTab leverages an asymmetric encoder-decoder framework to decouple mutual and salient features among data pairs, resulting in more representative embeddings. These embeddings, in turn, contribute to better decision boundaries and lead to improved results in downstream tasks. To validate the effectiveness of SwitchTab, we conduct extensive experiments across various domains involving tabular data. The results showcase superior performance in end-to-end prediction tasks with fine-tuning. Moreover, we demonstrate that pre-trained salient embeddings can be utilized as plug-and-play features to enhance the performance of various traditional classification methods (e.g., Logistic Regression, XGBoost, etc.). Lastly, we highlight the capability of SwitchTab to create explainable representations through visualization of decoupled mutual and salient features in the latent space.