One Graph, Multiple Gains: Single High-Quality Item-Item Graph for Multimodal Recommendation

2026-07-27

AI Summary

This work addresses the limitations of existing item-item graphs, which are often noisy and restricted to single-propagation tasks, thereby hindering their effectiveness in multimodal recommendation. The authors propose a high-quality item-item graph construction method and systematically reuse this graph across three stages: representation enhancement, interaction graph augmentation, and optimization refinement. Key innovations include integrating semantic and co-occurrence signals for graph construction, triadic closure–based NCER edge reweighting, a residual item-item gating (RIG) mechanism, content-guided user-item graph expansion, and II-neighborhood BPR augmentation (INA). Extensive experiments demonstrate that the proposed approach significantly outperforms state-of-the-art models on four benchmark datasets, achieving faster inference, lower GPU memory consumption, and notably improved performance in cold-start and data-sparse scenarios.

Abstract

Multimodal recommendation leverages item multimodal features alongside collaborative signals to capture user preferences. While item-item graphs have become a key building block in advanced models, existing methods typically construct them with noisy similarity edges and limit their role to a single function of item-item representation propagation, leaving substantial potential untapped. In this paper, we propose IIMRec, a framework that constructs a single high-quality item-item graph during preprocessing and systematically reuses it across three stages of the recommendation pipeline: representation enhancement, interaction graph enhancement, and optimization enhancement. The graph is built by fusing semantic and co-occurrence signals, then refined via Neighborhood Consistency Edge Reweighting (NCER), which applies the triadic closure principle to amplify structurally reliable edges and suppress spurious ones. Once constructed, the graph is leveraged in three complementary ways: (1) Item-item propagation with a Residual II Gate (RIG) that adaptively controls per-item absorption of semantic neighborhood signals for representation enhancement; (2) A content-guided UI graph expansion that introduces virtual user-item edges through high-confidence semantic neighbors for interaction graph enhancement; (3) II-Neighbor BPR Augmentation (INA) that treats top neighbors of positive items as discounted soft positives for optimization enhancement. We provide theoretical analysis showing that NCER reduces the spectral noise-to-signal ratio, RIG converges to a non-degenerate gating regime, and INA yields a tighter generalization bound. Extensive experiments on four datasets demonstrate that IIMRec consistently outperforms state-of-the-art baselines while running faster and consuming less GPU memory, with particularly strong gains under cold-start and sparse-interaction conditions.

Problem

• multimodal recommendation
• item-item graph
• graph construction
• noisy edges
• representation propagation

Innovation

• item-item graph
• multimodal recommendation
• edge reweighting
• graph propagation
• cold-start recommendation