How to Perform Reproducible Experiments in the ELLIOT Recommendation Framework: Data Processing, Model Selection, and Performance Evaluation
Entidad
UAM. Departamento de Ingeniería InformáticaEditor
CEURFecha de edición
2021-10-05Cita
How to Perform Reproducible Experiments in the ELLIOT Recommendation Framework: Data Processing, Model Selection, and Performance Evaluation Discussion Paper IRR (2021)Materias
Recommender Systems; Reproducibility; Adversarial Learning; Visual Recommenders; Knowledge Graphs; InformáticaDerechos
© The author(s)Resumen
Recommender Systems have shown to be an efective way to alleviate the over-choice problem and provide
accurate and tailored recommendations. However, the impressive number of proposed recommendation
algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental
evaluation particularly challenging. ELLIOT is a comprehensive recommendation framework that aims
to run and reproduce an entire experimental pipeline by processing a simple confguration fle. The
framework loads, flters, and splits the data considering a vast set of strategies. Then, it optimizes
hyperparameters for several recommendation algorithms, selects the best models, compares them with
the baselines, computes metrics spanning from accuracy to beyond-accuracy, bias, and fairness, and
conducts statistical analysis. The aim is to provide researchers a tool to ease all the experimental
evaluation phases (and make them reproducible), from data reading to results collection. ELLIOT is
freely available on GitHub at https://github.com/sisinflab/elliot
Lista de ficheros
Google Scholar:Vito Walter, Anelli
-
Bellogin Kouki, Alejandro
-
Ferrara, Antonio
-
Malitesta, Daniele
-
Merra, Felice Antonio
-
Pomo, Claudio
-
Donini, Francesco Maria
-
Sciascio, Eugenio Di
-
Noia, Tommaso Di
Lista de colecciones del ítem
Registros relacionados
Mostrando ítems relacionados por título, autor, creador y materia.