# Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation

arXiv: https://arxiv.org/abs/2602.20723 · HTML: https://mlsanity.com/paper/2602.20723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2010.10783/) (2020)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts](https://mlsanity.com/paper/2206.02770/) (2022)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [Disentangled Graph Collaborative Filtering](https://mlsanity.com/paper/2007.01764/) (2020)
- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks](https://mlsanity.com/paper/2202.05306/) (2022)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [Mining Latent Structures for Multimedia Recommendation](https://mlsanity.com/paper/2104.09036/) (2021)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback](https://mlsanity.com/paper/2111.02036/) (2021)
- [Bootstrap Latent Representations for Multi-modal Recommendation](https://mlsanity.com/paper/2207.05969/) (2022)
- [A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation](https://mlsanity.com/paper/2211.06924/) (2022)
- [Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models](https://mlsanity.com/paper/2404.10237/) (2024)
- [A Content-Driven Micro-Video Recommendation Dataset at Scale](https://mlsanity.com/paper/2309.15379/) (2023)
- [Multi-View Graph Convolutional Network for Multimedia Recommendation](https://mlsanity.com/paper/2308.03588/) (2023)
- [GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts](https://mlsanity.com/paper/2412.11085/) (2024)
- [MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts](https://mlsanity.com/paper/2311.09580/) (2023)
- [MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation](https://mlsanity.com/paper/2402.19407/) (2024)
- [Disentangled Multimodal Representation Learning for Recommendation](https://mlsanity.com/paper/2203.05406/) (2022)
- [Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation](https://mlsanity.com/paper/2412.14978/) (2024)
- [COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation](https://mlsanity.com/paper/2504.04452/) (2025)
- [GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation](https://mlsanity.com/paper/2407.12338/) (2024)

## Abstract (arXiv)

Multimodal recommenders combine collaborative behavior with visual and textual item evidence, whose usefulness varies across user-item interactions. Independently trained source-specific diagnostic probes partition held-out interactions into behavior-, appearance-, semantics-, and mixed-evidence regimes across five benchmarks, within which capacity-matched fixed fusion rules exhibit systematic regime-dependent performance crossovers. This diagnostic observation motivates MAGNET, a multimodal graph recommender with two core mechanisms. First, a calibrated expert bank organizes trainable experts by anchor source (behavior, appearance, or semantics) and fusion family (dominant, balanced, or complementary), while an interaction-conditioned router selects a sparse composition using all three evidence sources. Second, an entropy-triggered, coverage-aware progressive schedule decouples population-level routing-mass coverage from per-instance decisiveness, transitioning from broad routing exploration to confident specialization once sufficient coverage is sustained, while preserving coverage thereafter. MAGNET separately encodes the observed interaction graph and a filtered content-induced structural view, applying cross-view alignment after independent propagation. We evaluate MAGNET on four Amazon domains and the non-Amazon MicroLens-100K benchmark, including tail-item and low-history warm-start user evaluation alongside matched expert-design controls. Under the shared-feature, fixed-split protocol, MAGNET-DV exceeds the strongest protocol-compatible non-MAGNET baseline in every reported main-table cell, supported by seed-wise difference tests. Both the fixed and KL-anchored structured variants achieve higher five-seed mean NDCG@20 than matched homogeneous and free-mixture alternatives across all five datasets. MAGNET supports route-level diagnostics through explicit expert semantics.