SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Chaejeong, Choi, Jeongwhan, Wi, Hyowon, Cho, Sung-Bae, Park, Noseong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910751691636736
author Lee, Chaejeong
Choi, Jeongwhan
Wi, Hyowon
Cho, Sung-Bae
Park, Noseong
author_facet Lee, Chaejeong
Choi, Jeongwhan
Wi, Hyowon
Cho, Sung-Bae
Park, Noseong
contents Graph-based collaborative filtering (CF) has emerged as a promising approach in recommender systems. Despite its achievements, graph-based CF models face challenges due to data sparsity and negative sampling. In this paper, we propose a novel Stochastic sampling for i) COntrastive views and ii) hard NEgative samples (SCONE) to overcome these issues. SCONE generates dynamic augmented views and diverse hard negative samples via a unified stochastic sampling approach based on score-based generative models. Our extensive experiments on 6 benchmark datasets show that SCONE consistently outperforms state-of-the-art baselines. SCONE shows efficacy in addressing user sparsity and item popularity issues, while enhancing performance for both cold-start users and long-tail items. Furthermore, our approach improves the diversity of the recommendation and the uniformity of the representations. The code is available at https://github.com/jeongwhanchoi/SCONE.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00287
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
Lee, Chaejeong
Choi, Jeongwhan
Wi, Hyowon
Cho, Sung-Bae
Park, Noseong
Information Retrieval
Artificial Intelligence
Machine Learning
Graph-based collaborative filtering (CF) has emerged as a promising approach in recommender systems. Despite its achievements, graph-based CF models face challenges due to data sparsity and negative sampling. In this paper, we propose a novel Stochastic sampling for i) COntrastive views and ii) hard NEgative samples (SCONE) to overcome these issues. SCONE generates dynamic augmented views and diverse hard negative samples via a unified stochastic sampling approach based on score-based generative models. Our extensive experiments on 6 benchmark datasets show that SCONE consistently outperforms state-of-the-art baselines. SCONE shows efficacy in addressing user sparsity and item popularity issues, while enhancing performance for both cold-start users and long-tail items. Furthermore, our approach improves the diversity of the recommendation and the uniformity of the representations. The code is available at https://github.com/jeongwhanchoi/SCONE.
title SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.00287