Balanced Multimodal Learning via Mutual Information

TL;DR

This paper introduces a unified framework for balanced multimodal learning that uses mutual information to address modality imbalance, improving performance especially in biological data analysis.

Contribution

The study proposes a novel approach combining cross-modal knowledge distillation and multitask-like training to effectively mitigate modality imbalance in multimodal learning.

Findings

Enhanced model performance on imbalanced multimodal datasets

Effective utilization of mutual information for modality calibration

Improved predictive accuracy in biological data analysis

Abstract

Multimodal learning has increasingly become a focal point in research, primarily due to its ability to integrate complementary information from diverse modalities. Nevertheless, modality imbalance, stemming from factors such as insufficient data acquisition and disparities in data quality, has often been inadequately addressed. This issue is particularly prominent in biological data analysis, where datasets are frequently limited, costly to acquire, and inherently heterogeneous in quality. Conventional multimodal methodologies typically fall short in concurrently harnessing intermodal synergies and effectively resolving modality conflicts. In this study, we propose a novel unified framework explicitly designed to address modality imbalance by utilizing mutual information to quantify interactions between modalities. Our approach adopts a balanced multimodal learning strategy comprising two key stages: cross-modal knowledge distillation (KD) and a multitask-like training paradigm. During the cross-modal KD pretraining phase, stronger modalities are leveraged to enhance the predictive capabilities of weaker modalities. Subsequently, our primary training phase employs a multitask-like learning mechanism, dynamically calibrating gradient contributions based on modality-specific performance metrics and intermodal mutual information. This approach effectively alleviates modality imbalance, thereby significantly improving overall multimodal model performance.