# Semantic Item Graph Enhancement for Multimodal Recommendation

arXiv: https://arxiv.org/abs/2508.06154 · HTML: https://mlsanity.com/paper/2508.06154/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 17 of 17)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [Mining Latent Structures for Multimedia Recommendation](https://mlsanity.com/paper/2104.09036/) (2021)
- [GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback](https://mlsanity.com/paper/2111.02036/) (2021)
- [A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation](https://mlsanity.com/paper/2211.06924/) (2022)
- [A Content-Driven Micro-Video Recommendation Dataset at Scale](https://mlsanity.com/paper/2309.15379/) (2023)
- [LGMRec: Local and Global Graph Learning for Multimodal Recommendation](https://mlsanity.com/paper/2312.16400/) (2023)
- [Multi-View Graph Convolutional Network for Multimedia Recommendation](https://mlsanity.com/paper/2308.03588/) (2023)
- [Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation](https://mlsanity.com/paper/2111.00678/) (2021)
- [SelfCF: A Simple Framework for Self-supervised Collaborative Filtering](https://mlsanity.com/paper/2107.03019/) (2021)
- [Collaborative Similarity Embedding for Recommender Systems](https://mlsanity.com/paper/1902.06188/) (2019)
- [Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback](https://mlsanity.com/paper/2406.12501/) (2024)
- [Layer-refined Graph Convolutional Networks for Recommendation](https://mlsanity.com/paper/2207.11088/) (2022)
- [Advancing Sustainability via Recommender Systems: A Survey](https://mlsanity.com/paper/2411.07658/) (2024)
- [Disentangled Graph Variational Auto-Encoder for Multimodal Recommendation with Interpretability](https://mlsanity.com/paper/2402.16110/) (2024)
- [Communication-Efficient Federated Knowledge Graph Embedding with Entity-Wise Top-K Sparsification](https://mlsanity.com/paper/2406.13225/) (2024)
- [Learning Item Representations Directly from Multimodal Features for Effective Recommendation](https://mlsanity.com/paper/2505.04960/) (2025)

## Built on by (most cited first, 2 of 2)

- [EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation](https://mlsanity.com/paper/2508.16170/) (2025)
- [Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States](https://mlsanity.com/paper/2509.11247/) (2025)

## Abstract (arXiv)

Multimodal recommendation systems have attracted increasing attention for their improved performance by leveraging items' multimodal information. Prior methods often build modality-specific item-item semantic graphs from raw modality features and use them as supplementary structures alongside the user-item interaction graph to enhance user preference learning. However, these semantic graphs suffer from semantic deficiencies, including (1) insufficient modeling of collaborative signals among items and (2) structural distortions introduced by noise in raw modality features, ultimately compromising performance. To address these issues, we first extract collaborative signals from the interaction graph and infuse them into each modality-specific item semantic graph to enhance semantic modeling. Then, we design a modulus-based personalized embedding perturbation mechanism that injects perturbations with modulus-guided personalized intensity into embeddings to generate contrastive views. This enables the model to learn noise-robust representations through contrastive learning, thereby reducing the effect of structural noise in semantic graphs. Besides, we propose a dual representation alignment mechanism that first aligns multiple semantic representations via a designed Anchor-based InfoNCE loss using behavior representations as anchors, and then aligns behavior representations with the fused semantics by standard InfoNCE, to ensure representation consistency. Extensive experiments on four benchmark datasets validate the effectiveness of our framework.