Controlling Diversity at Inference: Guiding Diffusion Recommender Models with Targeted Category Preferences
Authors:
- Gwangseok HanGHGwangseok Han
- Wonbin KweonWKWonbin Kweon
- Minsoo KimMKMinsoo Kim
- Hwanjo YuHYHwanjo Yu
Preprint
Abstract
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 \textbf{D3Rec} (\underline{D}isentangled \underline{D}iffusion model for \underline{D}iversified \underline{Rec}ommendation), 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.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- User-controllable Recommendation Against Filter Bubbles2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- DGCN: Diversified Recommendation with Graph Convolutional Networks2021
- Controllable Multi-Interest Framework for Recommendation2020
- Focal Loss for Dense Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Generating and Personalizing Bundle Recommendations on Steam2017
- The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing SummariesACM SIGIR Forum, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Solving the apparent diversity-accuracy dilemma of recommender systemsProceedings of the National Academy of Sciences, 2010
- Improving recommendation lists through topic diversification2005