Efficient Low-rank Multimodal Fusion with Modality-Specific Factors

TL;DR

This paper introduces a low-rank tensor approach for multimodal fusion that enhances computational efficiency while maintaining competitive performance across sentiment, speaker trait, and emotion recognition tasks.

Contribution

It proposes a novel low-rank multimodal fusion method that reduces tensor complexity, improving efficiency without sacrificing accuracy.

Findings

Achieves competitive results on three multimodal tasks.

Significantly reduces computational complexity.

Performs robustly across various low-rank configurations.

Abstract

Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact multimodal representation. Previous research in this field has exploited the expressiveness of tensors for multimodal representation. However, these methods often suffer from exponential increase in dimensions and in computational complexity introduced by transformation of input into tensor. In this paper, we propose the Low-rank Multimodal Fusion method, which performs multimodal fusion using low-rank tensors to improve efficiency. We evaluate our model on three different tasks: multimodal sentiment analysis, speaker trait analysis, and emotion recognition. Our model achieves competitive results on all these tasks while drastically reducing computational complexity. Additional experiments also show that our model can perform robustly for a wide range of low-rank settings, and is indeed much more efficient in both training and inference compared to other methods that utilize tensor representations.