Part 1. Reproducibility
This page contains the useful resources for part 1 of the tutorial: Reproducibility.
Duration: 60 minutes
Panelist: Claudio Pomo
- [Hands-on #1] Implementation and reproducibility of GNNs-based recsys in Elliot with PyG and reproducibility issues: 35 minutes
- Performance comparison of GNNs-based approaches to traditional recommendation systems: 25 minutes
Papers
- Vito Walter Anelli, Daniele Malitesta, Claudio Pomo, Alejandro BellogĂn, Eugenio Di Sciascio, Tommaso Di Noia:
Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis. RecSys 2023: 350-361.
[paper][code] - Daniele Malitesta, Claudio Pomo, Vito Walter Anelli, Tommaso Di Noia, Antonio Ferrara:
An Out-of-the-Box Application for Reproducible Graph Collaborative Filtering extending the Elliot Framework. UMAP (Adjunct Publication) 2023: 12-15.
[paper][code]