LRMM: Learning to Recommend with Missing Modalities

TL;DR

LRMM is a new framework for multimodal recommendation that effectively handles missing modalities and cold-start issues by using modality dropout and a multimodal autoencoder, achieving state-of-the-art results.

Contribution

The paper introduces LRMM, a novel approach that addresses missing modalities and cold-start problems in multimodal recommendation systems.

Findings

LRMM outperforms existing methods on Amazon data.

LRMM is more robust to data sparsity and cold-start scenarios.

LRMM effectively imputes missing modalities using m-auto.

Abstract

Multimodal learning has shown promising performance in content-based recommendation due to the auxiliary user and item information of multiple modalities such as text and images. However, the problem of incomplete and missing modality is rarely explored and most existing methods fail in learning a recommendation model with missing or corrupted modalities. In this paper, we propose LRMM, a novel framework that mitigates not only the problem of missing modalities but also more generally the cold-start problem of recommender systems. We propose modality dropout (m-drop) and a multimodal sequential autoencoder (m-auto) to learn multimodal representations for complementing and imputing missing modalities. Extensive experiments on real-world Amazon data show that LRMM achieves state-of-the-art performance on rating prediction tasks. More importantly, LRMM is more robust to previous methods in alleviating data-sparsity and the cold-start problem.