التفاصيل البيبلوغرافية
| العنوان: |
Joint embedding–classifier learning for interpretable collaborative filtering. |
| المؤلفون: |
Réda, Clémence1 (AUTHOR) clemence.reda@uni-rostock.de, Vie, Jill-Jênn2 (AUTHOR) jill-jenn.vie@inria.fr, Wolkenhauer, Olaf1,3,4 (AUTHOR) olaf.wolkenhauer@uni-rostock.de |
| المصدر: |
BMC Bioinformatics. 1/22/2025, Vol. 26 Issue 1, p1-34. 34p. |
| مصطلحات موضوعية: |
*RECOMMENDER systems, *DRUG repositioning, *GENE expression, *COLLABORATIVE learning, *ENCODING |
| مستخلص: |
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. [ABSTRACT FROM AUTHOR] |
| قاعدة البيانات: |
Academic Search Index |
Full Text Finder