MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation

TL;DR

MoToRec introduces a novel sparse-regularized multimodal tokenization framework using a RQ-VAE to generate interpretable semantic tokens, significantly improving cold-start recommendation performance by disentangling representations and prioritizing cold-start items.

Contribution

The paper proposes MoToRec, a new framework that transforms multimodal recommendation into discrete semantic tokenization with a sparsely-regularized RQ-VAE, enhancing cold-start recommendation accuracy.

Findings

MoToRec outperforms state-of-the-art methods in cold-start scenarios.

Disentangled semantic tokens improve interpretability and robustness.

Adaptive rarity amplification effectively prioritizes cold-start items.

Abstract

Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item cold-start problem significantly impair performance, particularly for new items with limited or no interaction history. While multimodal content offers a promising solution, existing methods result in suboptimal representations for new items due to noise and entanglement in sparse data. To address this, we transform multimodal recommendation into discrete semantic tokenization. We present Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation (MoToRec), a framework centered on a sparsely-regularized Residual Quantized Variational Autoencoder (RQ-VAE) that generates a compositional semantic code of discrete, interpretable tokens, promoting disentangled representations. MoToRec's architecture is enhanced by three synergistic components: (1) a sparsely-regularized RQ-VAE that promotes disentangled representations, (2) a novel adaptive rarity amplification that promotes prioritized learning for cold-start items, and (3) a hierarchical multi-source graph encoder for robust signal fusion with collaborative signals. Extensive experiments on three large-scale datasets demonstrate MoToRec's superiority over state-of-the-art methods in both overall and cold-start scenarios. Our work validates that discrete tokenization provides an effective and scalable alternative for mitigating the long-standing cold-start challenge.