# Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation

arXiv: https://arxiv.org/abs/2301.12097 · HTML: https://mlsanity.com/paper/2301.12097/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2023.

## Built on by (most cited first, 15 of 15)

- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima](https://mlsanity.com/paper/2402.11262/) (2024)
- [Pareto Invariant Representation Learning for Multimedia Recommendation](https://mlsanity.com/paper/2308.04706/) (2023)
- [Bundle Recommendation with Item-level Causation-enhanced Multi-view Learning](https://mlsanity.com/paper/2408.08906/) (2024)
- [Dreaming User Multimodal Representation Guided by The Platonic Representation Hypothesis for Micro-Video Recommendation](https://mlsanity.com/paper/2410.03538/) (2024)
- [Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation](https://mlsanity.com/paper/2508.08042/) (2025)
- [MDE: Modality Discrimination Enhancement for Multi-modal Recommendation](https://mlsanity.com/paper/2502.18481/) (2025)
- [Token-Efficient Item Representation via Images for LLM Recommender Systems](https://mlsanity.com/paper/2503.06238/) (2025)
- [Combating the Bucket Effect:Multi-Knowledge Alignment for Medication Recommendation](https://mlsanity.com/paper/2504.18096/) (2025)
- [Structurally Refined Graph Transformer for Multimodal Recommendation](https://mlsanity.com/paper/2511.00584/) (2025)
- [Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion](https://mlsanity.com/paper/2511.02113/) (2025)
- [From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation](https://mlsanity.com/paper/2511.19176/) (2025)
- [Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems](https://mlsanity.com/paper/2603.12726/) (2026)
- [User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation](https://mlsanity.com/paper/2604.03014/) (2026)
- [Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks](https://mlsanity.com/paper/2605.06238/) (2026)

## Abstract (arXiv)

User interaction data in recommender systems is a form of dyadic relation that reflects the preferences of users with items. Learning the representations of these two discrete sets of objects, users and items, is critical for recommendation. Recent multimodal recommendation models leveraging multimodal features (e.g., images and text descriptions) have been demonstrated to be effective in improving recommendation accuracy. However, state-of-the-art models enhance the dyadic relations between users and items by considering either user-user or item-item relations, leaving the high-order relations of the other side (i.e., users or items) unexplored. Furthermore, we experimentally reveal that the current multimodality fusion methods in the state-of-the-art models may degrade their recommendation performance. That is, without tainting the model architectures, these models can achieve even better recommendation accuracy with uni-modal information. On top of the finding, we propose a model that enhances the dyadic relations by learning Dual RepresentAtions of both users and items via constructing homogeneous Graphs for multimOdal recommeNdation. We name our model as DRAGON. Specifically, DRAGON constructs the user-user graph based on the commonly interacted items and the item-item graph from item multimodal features. It then utilizes graph learning on both the user-item heterogeneous graph and the homogeneous graphs (user-user and item-item) to obtain the dual representations of users and items. To capture information from each modality, DRAGON employs a simple yet effective fusion method, attentive concatenation, to derive the representations of users and items. Extensive experiments on three public datasets and seven baselines show that DRAGON can outperform the strongest baseline by 22.03% on average. Various ablation studies are conducted on DRAGON to validate its effectiveness.