TablEye: Seeing small Tables through the Lens of Images
This addresses the challenge of few-shot learning for tabular data, which is important for domains with limited labeled data, though it appears incremental by adapting image-based methods.
The paper tackles the problem of few-shot learning on tabular data by proposing TablEye, a framework that transforms tabular data into images to leverage existing few-shot learning algorithms, resulting in performance improvements such as a 0.11 AUC gain over TabLLM in a 4-shot task and a 3.17% accuracy lead over STUNT in a 1-shot setting.
The exploration of few-shot tabular learning becomes imperative. Tabular data is a versatile representation that captures diverse information, yet it is not exempt from limitations, property of data and model size. Labeling extensive tabular data can be challenging, and it may not be feasible to capture every important feature. Few-shot tabular learning, however, remains relatively unexplored, primarily due to scarcity of shared information among independent datasets and the inherent ambiguity in defining boundaries within tabular data. To the best of our knowledge, no meaningful and unrestricted few-shot tabular learning techniques have been developed without imposing constraints on the dataset. In this paper, we propose an innovative framework called TablEye, which aims to overcome the limit of forming prior knowledge for tabular data by adopting domain transformation. It facilitates domain transformation by generating tabular images, which effectively conserve the intrinsic semantics of the original tabular data. This approach harnesses rigorously tested few-shot learning algorithms and embedding functions to acquire and apply prior knowledge. Leveraging shared data domains allows us to utilize this prior knowledge, originally learned from the image domain. Specifically, TablEye demonstrated a superior performance by outstripping the TabLLM in a 4-shot task with a maximum 0.11 AUC and a STUNT in a 1- shot setting, where it led on average by 3.17% accuracy.