Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910459389542400 |
|---|---|
| author | Anelli, Vito Walter Malitesta, Daniele Pomo, Claudio Bellogín, Alejandro Di Noia, Tommaso Di Sciascio, Eugenio |
| author_facet | Anelli, Vito Walter Malitesta, Daniele Pomo, Claudio Bellogín, Alejandro Di Noia, Tommaso Di Sciascio, Eugenio |
| contents | 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 offline evaluations. 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_00404 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis Anelli, Vito Walter Malitesta, Daniele Pomo, Claudio Bellogín, Alejandro Di Noia, Tommaso Di Sciascio, Eugenio Information Retrieval Artificial Intelligence 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 offline evaluations. 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. |
| title | Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2308.00404 |