Salvato in:
Dettagli Bibliografici
Autori principali: Mhedhbi, Eya, Mourchid, Youssef, Othmani, Alice
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.10500
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912328562245632
author Mhedhbi, Eya
Mourchid, Youssef
Othmani, Alice
author_facet Mhedhbi, Eya
Mourchid, Youssef
Othmani, Alice
contents This paper introduces a cutting-edge method for enhancing recommender systems through the integration of generative self-supervised learning (SSL) with a Residual Graph Transformer. Our approach emphasizes the importance of superior data enhancement through the use of pertinent pretext tasks, automated through rationale-aware SSL to distill clear ways of how users and items interact. The Residual Graph Transformer incorporates a topology-aware transformer for global context and employs residual connections to improve graph representation learning. Additionally, an auto-distillation process refines self-supervised signals to uncover consistent collaborative rationales. Experimental evaluations on multiple datasets demonstrate that our approach consistently outperforms baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Auto-Distillation and Generative Self-Supervised Learning in Residual Graph Transformers for Enhanced Recommender Systems
Mhedhbi, Eya
Mourchid, Youssef
Othmani, Alice
Information Retrieval
Artificial Intelligence
Machine Learning
This paper introduces a cutting-edge method for enhancing recommender systems through the integration of generative self-supervised learning (SSL) with a Residual Graph Transformer. Our approach emphasizes the importance of superior data enhancement through the use of pertinent pretext tasks, automated through rationale-aware SSL to distill clear ways of how users and items interact. The Residual Graph Transformer incorporates a topology-aware transformer for global context and employs residual connections to improve graph representation learning. Additionally, an auto-distillation process refines self-supervised signals to uncover consistent collaborative rationales. Experimental evaluations on multiple datasets demonstrate that our approach consistently outperforms baseline methods.
title Leveraging Auto-Distillation and Generative Self-Supervised Learning in Residual Graph Transformers for Enhanced Recommender Systems
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.10500