# MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusion

arXiv: https://arxiv.org/abs/2609.01619 · HTML: https://mlsanity.com/paper/2609.01619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion recommenders, one of 14 directions in Diffusion models.
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Placed in

- Diffusion models / [Diffusion recommenders](https://mlsanity.com/diffusion/diffusion-recommenders/)

## Builds on (most cited first, 19 of 19)

- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [DiffuRec: A Diffusion Model for Sequential Recommendation](https://mlsanity.com/paper/2304.00686/) (2023)
- [Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks](https://mlsanity.com/paper/1706.04148/) (2017)
- [Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion](https://mlsanity.com/paper/2310.20453/) (2023)
- [MDM: Molecular Diffusion Model for 3D Molecule Generation](https://mlsanity.com/paper/2209.05710/) (2022)
- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [DiffKG: Knowledge Graph Diffusion Model for Recommendation](https://mlsanity.com/paper/2312.16890/) (2023)
- [Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation](https://mlsanity.com/paper/2307.04571/) (2023)
- [Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation](https://mlsanity.com/paper/2103.10693/) (2021)
- [DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models](https://mlsanity.com/paper/2408.12153/) (2024)
- [LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation](https://mlsanity.com/paper/2409.19925/) (2024)
- [MILP-StuDio: MILP Instance Generation via Block Structure Decomposition](https://mlsanity.com/paper/2410.22806/) (2024)
- [Accelerating PDE Data Generation via Differential Operator Action in Solution Space](https://mlsanity.com/paper/2402.05957/) (2024)
- [Distinguished Quantized Guidance for Diffusion-based Sequence Recommendation](https://mlsanity.com/paper/2501.17670/) (2025)
- [DiffCL: A Diffusion-Based Contrastive Learning Framework with Semantic Alignment for Multimodal Recommendations](https://mlsanity.com/paper/2501.01066/) (2025)
- [Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics](https://mlsanity.com/paper/2406.09740/) (2024)

## Abstract (arXiv)

We propose a novel Multi-Interest Sequence Recommendation Framework with underlineMasking underlineGNN-Guided underlineDiffusion Model (MGDiff), designed to generate accurate, bias-free user interest information during the diffusion process. First, we propose a semantics-enhanced Dual-layer Semantic Guidance (DSG) framework, which decomposes guidance into two synergistic stages: extracting latent item semantics and decoupling multidimensional user intent. We design a Weight-adaptive Masking Graph Neural Network reconstructs missing links to uncover deep item relationships beyond superficial co-occurrence, while a Dynamic Multi-Expert Network projects user preferences into distinct semantic subspaces to suppress irrelevant interference. This hierarchical design yields structured guidance that significantly improves the generation accuracy of diffusion models. Second, We propose a Popularity-Aware Guidance (PAG) mechanism that performs spatial geometric adjustments on the outputs of diffusion models: by using item popularity as a differentiable adjustment signal to recalibrate similarity metrics, we enable DMs to generate diverse recommendations free from popularity bias. Finally, we compare MGDiff with multiple baseline models across four widely used datasets, demonstrating its superior performance and validating its effectiveness.