# Controlling Diversity at Inference: Guiding Diffusion Recommender Models with Targeted Category Preferences

arXiv: https://arxiv.org/abs/2411.11240 · HTML: https://mlsanity.com/paper/2411.11240/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2024.

## Built on by (most cited first, 4 of 4)

- [Diffusion Models in Recommendation Systems: A Survey](https://mlsanity.com/paper/2501.10548/) (2025)
- [Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation](https://mlsanity.com/paper/2509.26063/) (2025)
- [Collaborative Diffusion Model for Recommender System](https://mlsanity.com/paper/2501.18997/) (2025)
- [FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models](https://mlsanity.com/paper/2609.36671/) (2026)

## Abstract (arXiv)

Diversity control is an important task to alleviate bias amplification and filter bubble problems. The desired degree of diversity may fluctuate based on users' daily moods or business strategies. However, existing methods for controlling diversity often lack flexibility, as diversity is decided during training and cannot be easily modified during inference. We propose D3Rec (underlineDisentangled underlineDiffusion model for underlineDiversified underlineRecommendation), an end-to-end method that controls the accuracy-diversity trade-off at inference. D3Rec meets our three desiderata by (1) generating recommendations based on category preferences, (2) controlling category preferences during the inference phase, and (3) adapting to arbitrary targeted category preferences. In the forward process, D3Rec removes category preferences lurking in user interactions by adding noises. Then, in the reverse process, D3Rec generates recommendations through denoising steps while reflecting desired category preferences. Extensive experiments on real-world and synthetic datasets validate the effectiveness of D3Rec in controlling diversity at inference.