Projects per year
Abstract
Using graph models with relational information in recommender systems has shown promising results. Yet, most methods are transductive, i.e., they are based on dimensionality reduction architectures. Hence, they require heavy retraining every time new items or users are added. Conversely, inductive methods promise to solve these issues. Nonetheless, all inductive methods rely only on interactions, making recommendations for users with few interactions sub-optimal and even impossible for new items. Therefore, we focus on inductive methods able to also exploit knowledge graphs (KGs). In this work, we propose SimpleRec, a strong baseline that uses a graph neural network and a KG to provide better recommendations than related inductive methods for new users and items. We show that it is unnecessary to create complex model architectures for user representations, but it is enough to allow users to be represented by the few ratings they provide and the indirect connections among them without any user metadata. As a result, we re-evaluate state-of-the-art methods, identify better evaluation protocols, highlight unwarranted conclusions from previous proposals, and showcase a novel, stronger baseline for this task.
Original language | English |
---|
Publisher | arXiv |
---|---|
DOIs | |
Publication status | Published - 13 Sept 2022 |
Fingerprint
Dive into the research topics of 'Simple and Powerful Architecture for Inductive Recommendation Using Knowledge Graph Convolutions'. Together they form a unique fingerprint.-
Poul Due Jensen Professorate in Big Data and Artificial Intelligence
Hose, K. (PI), Jendal, T. E. (Project Participant) & Hansen, E. R. (Project Participant)
01/11/2019 → 31/12/2025
Project: Research
-
EDAO: EDAO: Example Driven Analytics for Open Knowledge Graphs
Lissandrini, M. (PI), Pedersen, T. B. (Supervisor) & Hose, K. (Other)
15/09/2019 → 14/09/2021
Project: Research
-