Effectiveness of Deep Image Embedding Clustering Methods on Tabular Data

Deep learning methods are commonly benchmarked on image data sets, which may not be suitable or effective baselines for non-image tabular data. In this paper, we take a data-centric view to perform one of the first studies on deep embedding clustering of tabular data. Eight clustering and state-of-the-art embedding clustering methods proposed for image data sets are tested on seven tabular data sets. Our results reveal that traditional clustering ranks second out of eight methods on tabular data and is superior to most deep embedding clustering baselines. Our observation aligns with the literature that traditional machine learning of tabular data is still more effective than deep learning. Therefore, state-of-the-art embedding clustering methods should consider data-centric custom learning architectures and algorithms for tabular data.