Multimodal Representation Learning using Adaptive Graph Construction

Abstract

Multimodal contrastive learning train neural networks by levergaing data from heterogeneous sources such as images and text. Yet, many current multimodal learning architectures cannot generalize to an arbitrary number of modalities and need to be hand-constructed. We propose AutoBIND, a novel contrastive learning framework that can learn representations from an arbitrary number of modalites through graph optimization. We evaluate AutoBIND on Alzhiemer's disease detection because it has real-world medical applicability and it contains a broad range of data modalities. We show that AutoBIND outperforms previous methods on this task, highlighting the generalizablility of the approach.