# Preference Diffusion for Recommendation

arXiv: https://arxiv.org/abs/2410.13117 · HTML: https://mlsanity.com/paper/2410.13117/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 80 of its 99 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 30 of 80)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)

## Built on by (most cited first, 9 of 9)

- [FlowRec: Prior-Informed Flow Matching for Efficient Sequential Recommendation Generation](https://mlsanity.com/paper/2508.17618/) (2025)
- [Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation](https://mlsanity.com/paper/2509.26063/) (2025)
- [On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders](https://mlsanity.com/paper/2510.17245/) (2025)
- [When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation](https://mlsanity.com/paper/2511.18717/) (2025)
- [Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph](https://mlsanity.com/paper/2601.23233/) (2026)
- [Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation](https://mlsanity.com/paper/2606.01670/) (2026)
- [Population-Level Generative Modeling for Ranking Data](https://mlsanity.com/paper/2608.08422/) (2026)
- [GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2609.02162/) (2026)
- [OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2610.16038/) (2026)

## Abstract (arXiv)

Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. PreferDiff transforms BPR into a log-likelihood ranking objective and integrates multiple negative samples to better capture user preferences. Specifically, we employ variational inference to handle the intractability through minimizing the variational upper bound and replaces MSE with cosine error to improve alignment with recommendation tasks. Finally, we balance learning generation and preference to enhance the training stability of DMs. PreferDiff offers three key benefits: it is the first personalized ranking loss designed specifically for DM-based recommenders and it improves ranking and faster convergence by addressing hard negatives. We also prove that it is theoretically connected to Direct Preference Optimization which indicates that it has the potential to align user preferences in DM-based recommenders via generative modeling. Extensive experiments across three benchmarks validate its superior recommendation performance and commendable general sequential recommendation capabilities. Our codes are available at https://github.com/lswhim/PreferDiff.