TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data

TL;DR

TIP introduces a self-supervised pre-training framework that effectively learns multimodal representations from incomplete tabular and image data, improving classification performance in real-world scenarios.

Contribution

It proposes a novel self-supervised learning strategy and a versatile tabular encoder tailored for incomplete, heterogeneous data, advancing multimodal pre-training methods.

Findings

Outperforms state-of-the-art algorithms on natural and medical datasets.

Effective in both complete and incomplete data scenarios.

Demonstrates robustness to missing tabular data in multimodal classification.

Abstract

Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and incomplete, presenting significant modality disparities with images. Earlier works have mainly focused on simple modality fusion strategies in complete data scenarios, without considering the missing data issue, and thus are limited in practice. In this paper, we propose TIP, a novel tabular-image pre-training framework for learning multimodal representations robust to incomplete tabular data. Specifically, TIP investigates a novel self-supervised learning (SSL) strategy, including a masked tabular reconstruction task for tackling data missingness, and image-tabular matching and contrastive learning objectives to capture multimodal information. Moreover, TIP proposes a versatile tabular encoder tailored for incomplete, heterogeneous tabular data and a multimodal interaction module for inter-modality representation learning. Experiments are performed on downstream multimodal classification tasks using both natural and medical image datasets. The results show that TIP outperforms state-of-the-art supervised/SSL image/multimodal algorithms in both complete and incomplete data scenarios. Our code is available at https://github.com/siyi-wind/TIP.