EDGE-Rec: Efficient and Data-Guided Edge Diffusion For Recommender Systems Graphs
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-s...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2409.14689 |