Article Dans Une Revue BMC Bioinformatics Année : 2025

Joint Embedding-Classifier Learning for Interpretable Collaborative Filtering

Résumé

Background: Interpretability is a topical question in recommender systems, especially in healthcare applications. An interpretable classifier quantifies the importance of each input feature for the predicted item-user association in a non-ambiguous fashion. Results: We introduce the novel Joint Embedding Learning-classifier for improved Interpretability (JELI). By combining the training of a structured collaborative-filtering classifier and an embedding learning task, JELI predicts new user-item associations based on jointly learned item and user embeddings while providing feature-wise importance scores. Therefore, JELI flexibly allows the introduction of priors on the connections between users, items, and features. In particular, JELI simultaneously (a) learns feature, item, and user embeddings; (b) predicts new item-user associations; (c) provides importance scores for each feature. Moreover, JELI instantiates a generic approach to training recommender systems by encoding generic graph-regularization constraints. Conclusions: First, we show that the joint training approach yields a gain in the predictive power of the downstream classifier. Second, JELI can recover feature- association dependencies. Finally, JELI induces a restriction in the number of parameters compared to baselines in synthetic and drug-repurposing data sets.
Fichier principal
Vignette du fichier
reda2024joint.pdf (3.61 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04625183 , version 1 (26-06-2024)
hal-04625183 , version 2 (27-06-2024)
hal-04625183 , version 3 (09-10-2024)
hal-04625183 , version 4 (06-01-2025)

Licence

Identifiants

Citer

Clémence Réda, Jill-Jênn Vie, Olaf Wolkenhauer. Joint Embedding-Classifier Learning for Interpretable Collaborative Filtering. BMC Bioinformatics, 2025, 26 (1), pp.26. ⟨10.1186/s12859-024-06026-8⟩. ⟨hal-04625183v4⟩
127 Consultations
127 Téléchargements

Partager

More