PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning

arXiv:2404.00776v1 Announce Type: new
Abstract: We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch-based data structure to handle complex tabular data, introducing a model abstraction to enable modular implementation of tabular models, and allowing external foundation models to be incorporated to handle complex columns (e.g., LLMs for text columns). We demonstrate the usefulness of PyTorch Frame by implementing diverse tabular models in a modular …

abstract abstraction arxiv cs.db cs.lg data deep learning easy framework implementation modal modular multi-modal pytorch stat.ml tabular tabular data type