CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning

TL;DR

CyIN introduces a cyclic informative latent space and cross-modal translation to improve robustness and performance of multimodal learning models in scenarios with missing modalities.

Contribution

The paper proposes a novel CyIN framework that unifies complete and incomplete multimodal learning using cyclic information bottleneck and cross-modal reconstruction.

Findings

Outperforms existing methods on 4 multimodal datasets.

Effectively handles diverse incomplete modality scenarios.

Enhances robustness of multimodal models in real-world settings.

Abstract

Multimodal machine learning, mimicking the human brain's ability to integrate various modalities has seen rapid growth. Most previous multimodal models are trained on perfectly paired multimodal input to reach optimal performance. In real-world deployments, however, the presence of modality is highly variable and unpredictable, causing the pre-trained models in suffering significant performance drops and fail to remain robust with dynamic missing modalities circumstances. In this paper, we present a novel Cyclic INformative Learning framework (CyIN) to bridge the gap between complete and incomplete multimodal learning. Specifically, we firstly build an informative latent space by adopting token- and label-level Information Bottleneck (IB) cyclically among various modalities. Capturing task-related features with variational approximation, the informative bottleneck latents are purified for more efficient cross-modal interaction and multimodal fusion. Moreover, to supplement the missing information caused by incomplete multimodal input, we propose cross-modal cyclic translation by reconstruct the missing modalities with the remained ones through forward and reverse propagation process. With the help of the extracted and reconstructed informative latents, CyIN succeeds in jointly optimizing complete and incomplete multimodal learning in one unified model. Extensive experiments on 4 multimodal datasets demonstrate the superior performance of our method in both complete and diverse incomplete scenarios.