MMM4Rec: A Transfer-Efficient Framework for Multi-modal Sequential Recommendation

2025-06-03

AI Summary

To address high fine-tuning costs and negative transfer in cross-domain multimodal sequential recommendation, this paper proposes a lightweight and robust transfer learning framework. Methodologically, it introduces: (1) an algebraic constraint mechanism to enforce cross-domain semantic consistency; (2) a Cross-SSD temporal fusion module leveraging state space models (SSMs) to capture long-range dependencies; (3) dual-channel Fourier-adaptive filtering to suppress cross-modal noise propagation; and (4) shared projection with two-stage constrained optimization for cross-modal alignment. Evaluated on standard cross-domain benchmarks, the framework achieves a 31.78% improvement in NDCG@10 and accelerates fine-tuning convergence by 10×, significantly outperforming existing state-of-the-art methods.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Sequential Recommendation (SR) systems model user preferences by analyzing interaction histories. Although transferable multi-modal SR architectures demonstrate superior performance compared to traditional ID-based approaches, current methods incur substantial fine-tuning costs when adapting to new domains due to complex optimization requirements and negative transfer effects - a significant deployment bottleneck that hinders engineers from efficiently repurposing pre-trained models for novel application scenarios with minimal tuning overhead. We propose MMM4Rec (Multi-Modal Mamba for Sequential Recommendation), a novel multi-modal SR framework that incorporates a dedicated algebraic constraint mechanism for efficient transfer learning. By combining State Space Duality (SSD)'s temporal decay properties with a time-aware modeling design, our model dynamically prioritizes key modality information, overcoming limitations of Transformer-based approaches. The framework implements a constrained two-stage process: (1) sequence-level cross-modal alignment via shared projection matrices, followed by (2) temporal fusion using our newly designed Cross-SSD module and dual-channel Fourier adaptive filtering. This architecture maintains semantic consistency while suppressing noise propagation.MMM4Rec achieves rapid fine-tuning convergence with simple cross-entropy loss, significantly improving multi-modal recommendation accuracy while maintaining strong transferability. Extensive experiments demonstrate MMM4Rec's state-of-the-art performance, achieving the maximum 31.78% NDCG@10 improvement over existing models and exhibiting 10 times faster average convergence speed when transferring to large-scale downstream datasets.

Problem

• Reducing fine-tuning costs for multi-modal sequential recommendation models
• Overcoming negative transfer effects in model adaptation
• Improving transfer efficiency while maintaining recommendation accuracy

Innovation

• Algebraic constraint mechanism for efficient transfer
• State Space Duality with time-aware modeling
• Cross-SSD module and dual-channel Fourier filtering