Search papers, labs, and topics across Lattice.
This paper introduces MOTIF, a novel framework designed to tackle the challenges of cold-start multimodal recommendation by addressing user intent obscured by sparse interactions, topological isolation of cold items, and semantic drift in similarity-based item graphs. By leveraging Semantic Motivation Reasoning, Knowledge-enhanced Graph Reconstruction, and Weighted Graph Contrastive Learning, MOTIF effectively infers motivation semantics and reconstructs item topologies to enhance recommendation quality. Experimental results demonstrate that MOTIF outperforms existing methods, achieving up to a 6.07% relative improvement over the best-performing baseline across three multimodal benchmarks.
MOTIF achieves a significant boost in cold-start multimodal recommendation performance by inferring user motivations and reconstructing item relationships, outperforming state-of-the-art methods.
Cold-start multimodal recommendation faces three coupled challenges: (i) sparse interactions obscure user intent, (ii) cold items remain topologically isolated, and (iii) similarity-based item graphs may cause semantic drift. To address these issues, we propose MOTIF, a Motivation-guided Topology Inference framework for cold-start multimodal recommendation. MOTIF integrates Semantic Motivation Reasoning, Knowledge-enhanced Graph Reconstruction, Weighted Graph Contrastive Learning, and Semantic-Structural Alignment. It uses offline LLM reasoning to infer motivation semantics, reconstructs transferable item-item topology, and learns robust graph embeddings without injecting generated text into prediction. Experiments on three multimodal benchmarks show consistent gains over graph-based, multimodal, cold-start, and LLM-enhanced baselines, with up to 6.07% relative improvement over the strongest recent baseline.
