RecFusion: A Binomial Diffusion Process for 1D Data for Recommendation
This work addresses the challenge of adapting diffusion models to recommendation systems, which lack spatial correlations, and is incremental as it builds on existing diffusion methods for a specific domain.
The authors tackled the problem of applying diffusion models to recommendation systems by proposing RecFusion, a binomial diffusion process for 1D data, which achieved performance comparable to complex VAE baselines on MovieLens and Netflix datasets for top-n recommendation.
In this paper we propose RecFusion, which comprise a set of diffusion models for recommendation. Unlike image data which contain spatial correlations, a user-item interaction matrix, commonly utilized in recommendation, lacks spatial relationships between users and items. We formulate diffusion on a 1D vector and propose binomial diffusion, which explicitly models binary user-item interactions with a Bernoulli process. We show that RecFusion approaches the performance of complex VAE baselines on the core recommendation setting (top-n recommendation for binary non-sequential feedback) and the most common datasets (MovieLens and Netflix). Our proposed diffusion models that are specialized for 1D and/or binary setups have implications beyond recommendation systems, such as in the medical domain with MRI and CT scans.