Understanding the Ranking Loss for Recommendation with Sparse User Feedback

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Zhutian, Pan, Junwei, Zhang, Shangyu, Wang, Ximei, Xiao, Xi, Huang, Shudong, Xiao, Lei, Jiang, Jie
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916313714130944
author Lin, Zhutian
Pan, Junwei
Zhang, Shangyu
Wang, Ximei
Xiao, Xi
Huang, Shudong
Xiao, Lei
Jiang, Jie
author_facet Lin, Zhutian
Pan, Junwei
Zhang, Shangyu
Wang, Ximei
Xiao, Xi
Huang, Shudong
Xiao, Lei
Jiang, Jie
contents Click-through rate (CTR) prediction is a crucial area of research in online advertising. While binary cross entropy (BCE) has been widely used as the optimization objective for treating CTR prediction as a binary classification problem, recent advancements have shown that combining BCE loss with an auxiliary ranking loss can significantly improve performance. However, the full effectiveness of this combination loss is not yet fully understood. In this paper, we uncover a new challenge associated with the BCE loss in scenarios where positive feedback is sparse: the issue of gradient vanishing for negative samples. We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability. To validate our perspective, we conduct theoretical analysis and extensive empirical evaluations on public datasets. Additionally, we successfully integrate the ranking loss into Tencent's online advertising system, achieving notable lifts of 0.70% and 1.26% in Gross Merchandise Value (GMV) for two main scenarios. The code is openly accessible at: https://github.com/SkylerLinn/Understanding-the-Ranking-Loss.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14144
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding the Ranking Loss for Recommendation with Sparse User Feedback
Lin, Zhutian
Pan, Junwei
Zhang, Shangyu
Wang, Ximei
Xiao, Xi
Huang, Shudong
Xiao, Lei
Jiang, Jie
Information Retrieval
Click-through rate (CTR) prediction is a crucial area of research in online advertising. While binary cross entropy (BCE) has been widely used as the optimization objective for treating CTR prediction as a binary classification problem, recent advancements have shown that combining BCE loss with an auxiliary ranking loss can significantly improve performance. However, the full effectiveness of this combination loss is not yet fully understood. In this paper, we uncover a new challenge associated with the BCE loss in scenarios where positive feedback is sparse: the issue of gradient vanishing for negative samples. We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability. To validate our perspective, we conduct theoretical analysis and extensive empirical evaluations on public datasets. Additionally, we successfully integrate the ranking loss into Tencent's online advertising system, achieving notable lifts of 0.70% and 1.26% in Gross Merchandise Value (GMV) for two main scenarios. The code is openly accessible at: https://github.com/SkylerLinn/Understanding-the-Ranking-Loss.
title Understanding the Ranking Loss for Recommendation with Sparse User Feedback
topic Information Retrieval
url https://arxiv.org/abs/2403.14144