paper-with-me

Papers

Privileged Features Distillation at Taobao Recommendations

2019-07-11 · Chen Xu, Quan Li, Junfeng Ge, Jinyang Gao, Xiaoyong Yang, Changhua Pei, Fei Sun, Jian Wu, Hanxiao Sun, Wenwu Ou

Features play an important role in the prediction tasks of e-commerce recommendations. To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available. However, the consistency in turn neglects some discriminative features. For example, when estimating the conversion rate (CVR), i.e., the probability that a user would purchase the item if she clicked it, features like dwell time on the item detailed page are informative. However, CVR prediction should be conducted for on-line ranking before the click happens. Thus we cannot get such post-event features during serving. We define the features that are discriminative but only available during training as the privileged features. Inspired by the distillation techniques which bridge the gap between training and inference, in this work, we propose privileged features distillation (PFD). We train two models, i.e., a student model that is the same as the original one and a teacher model that additionally utilizes the privileged features. Knowledge distilled from the more accurate teacher is transferred to the student to improve its accuracy. During serving, only the student part is extracted and it relies on no privileged features. We conduct experiments on two fundamental prediction tasks at Taobao recommendations, i.e., click-through rate (CTR) at coarse-grained ranking and CVR at fine-grained ranking. By distilling the interacted features that are prohibited during serving for CTR and the post-event features for CVR, we achieve significant improvements over their strong baselines. During the on-line A/B tests, the click metric is improved by +5.0% in the CTR task. And the conversion metric is improved by +2.3% in the CVR task. Besides, by addressing several issues of training PFD, we obtain comparable training speed as the baselines without any distillation.

📄 PDF Abstract BibTeX arXiv:1907.05171

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Toward Understanding Privileged Features Distillation in Learning-to-Rank

2022-09-19 · Shuo Yang, Sujay Sanghavi, Holakou Rahmanian, Jan Bakus 외

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user…

Learning-To-RankRecommendation Systems

Calibration-compatible Listwise Distillation of Privileged Features for CTR Prediction

2023-12-14 · Xiaoqiang Gui, Yueyao Cheng, Xiang-Rong Sheng, Yunfeng Zhao 외

In machine learning systems, privileged features refer to the features that are available during offline training but inaccessible for online serving. Previous studies have recognized the importance of privileged feature…

Click-Through Rate Prediction

CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification

2024-10-03 · Jinghao Shi, Xiang Shen, Kaili Zhao, Xuedong Wang 외

Dense features, customized for different business scenarios, are essential in short video classification. However, their complexity, specific adaptation requirements, and high computational costs make them resource-inten…

Video Classification

USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations

2025-07-09 · Jiaqi Zheng, Cheng Guo, Yi Cao, Chaoqun Hou 외

Large-scale homepage recommendations face critical challenges from pseudo-negative samples caused by exposure bias, where non-clicks may indicate inattention rather than disinterest. Existing work lacks thorough analysis…

Marketing

Rethinking On-Policy Self-Distillation for Thinking Models

2026-07-06 · Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl 외 arxiv

Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems e…