Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
ACMDate
2023-09-18Citation
10.1145/3604915.3609489
RecSys’23: Proceedings of the 17th ACM Conference on Recommender Systems. ACM, Singapore,18–22 September, 2023
ISBN
979-8-4007-0241-9DOI
10.1145/3604915.3609489Funded by
This work was partially supported by the following projects: Secure Safe Apulia, MISECUP: I14E20000020001CTEMT-Casa delle Tecnologie Emergenti Comunedi Matera, CT_FINCONS_II, CT_FINCONS_III,OVS Fashion Retail Reloaded,LUTECH DIGITALE 4.0,PID2019-108965GB-I00.Editor's Version
https://doi.org/10.1145/3604915.3609489Subjects
Recommendation; Graph Collaborative Filtering; Reproducibility; InformáticaRights
© 2023 Copyright held by the owner/author(s).Abstract
The success of graph neural network-based models (GNNs) has significantly advanced recommender systems by effectively modeling users and items as a bipartite, undirected graph. However, many original graph-based works often adopt results from baseline papers without verifying their validity for the specific configuration under analysis. Our work addresses this issue by focusing on the replicability of results. We present a code that successfully replicates results from six popular and recent graph recommendation models (NGCF, DGCF, LightGCN, SGL, UltraGCN, and GFCF) on three common benchmark datasets (Gowalla, Yelp 2018, and Amazon Book). Additionally, we compare these graph models with traditional collaborative filtering models that historically performed well in offlineevaluations. Furthermore, we extend our study to two new datasets (Allrecipes and BookCrossing) that lack established setups in existing literature. As the performance on these datasets differs from the previous benchmarks, we analyze the impact of specific dataset characteristics on recommendation accuracy. By investigating the information flow from users’ neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure. The code to reproduce our experiments is available at: https://github.com/sisinflab/Graph-RSs-Reproducibility.
Files in this item
Google Scholar:Anelli, Vito Walter
-
Malitesta, Daniele
-
Pomo, Claudio
-
Bellogín, Alejandro
-
Di Sciascio, Eugenio
-
Di Noia, Tommaso
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.