Most recommender systems research focuses on binary historical user-item interaction encodings to predict future interactions. User features, item features, and interaction strengths remain largely under-utilized in this space or only indirectly utilized, despite proving largely effective in large-scale production recommendation systems. We propose a new attention mechanism, loosely based on the principles of collaborative filtering, called Row-Column Separable Attention RCSA to take advantage of real-valued interaction weights as well as user and item features directly. Building on this mechanism, we additionally propose a novel Graph Diffusion Transformer GDiT architecture which is trained to iteratively denoise the weighted interaction matrix of the user-item interaction graph directly. The weighted interaction matrix is built from the bipartite structure of the user-item interaction graph and corresponding edge weights derived from user-item rating interactions. Inspired by the recent progress in text-conditioned image generation, our method directly produces user-item rating predictions on the same scale as the original ratings by conditioning the denoising process on user and item features with a principled approach.
@article{arxiv.2409.14689,
title = {EDGE-Rec: Efficient and Data-Guided Edge Diffusion For Recommender Systems Graphs},
author = {Utkarsh Priyam and Hemit Shah and Edoardo Botta},
journal= {arXiv preprint arXiv:2409.14689},
year = {2024}
}