TANET 2024-Contrastive Learning Recommendation Systems with Time-Variant Objectives

機構典藏 > College of Business and Management > Department of Management Sciences > Proceeding > Item 987654321/126441

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126441

Title:	TANET 2024-Contrastive Learning Recommendation Systems with Time-Variant Objectives
Authors:	夏肇毅
Keywords:	Recommendation Systems;Contrastive Learning;Time Variant Objectives;TVO, GCN
Date:	2024-10-26
Issue Date:	2024-10-28 12:05:46 (UTC+8)
Publisher:	國立陽明交通大學
Abstract:	Recommendation systems have seen significant advancements with the application of machine learning techniques, yet challenges remain in maintaining optimal performance throughout training. Contrastive learning, while effective in enhancing user and item representations, often suffers from performance degradation over time. In this paper, we present a novel approach that incorporates time-variant objectives (TVO) to address this issue. By integrating a scheduler with various time-variant functions into the contrastive learning framework, we dynamically balance the recommendation loss and contrastive loss during training. This method stabilizes model performance and mitigates the typical decline observed in traditional approaches. Our experimental results show that the TVO-enhanced model achieves more reliable and precise recommendations compared to existing methods. This approach offers a promising solution for improving the consistency and accuracy of contrastive learning-based recommendation systems. Keywords: Recommendation Systems, Contrastive Learning, Time Variant Objectives, TVO, GCN
Relation:	TANET 2024 論文集
Appears in Collections:	[Department of Management Sciences] Proceeding

Files in This Item:

There are no files associated with this item.