相关实验视频
Updated: Sep 10, 2025

Measuring Delay Discounting in Humans Using an Adjusting Amount Task
Published on: January 9, 2016
在推系统中学习仪器变量表示
Zhirong Huang1, Shichao Zhang1, Debo Cheng2
1organization=Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, addressline=Guangxi Normal University, city=Guilin, postcode=541004, state=Guangxi, country=China; organization=Guangxi Key Lab of Multi-Source Information Mining and Security, addressline=Guangxi Normal University, city=Guilin, postcode=541004, state=Guangxi, country=China.
这项研究引入了一种基于因果关系的新算法 (DIVRS),用于对抗推系统的偏见. 通过学习仪器变量表示,提高准确性和多样性,DIVRS有效地消除了建议.
科学领域:
- 人工智能
- 机器学习
- 数据科学
背景情况:
- 推系统面临着数据偏差的挑战,特别是受欢迎程度偏差和隐藏的混因素,导致不准确和不多样化的建议.
- 现有的解散技术往往无法解决隐藏的混因素或需要预定义的仪器变量 (IV).
研究的目的:
- 提出一种新的基于因果关系的推算法,即DIVRS,该算法直接从用户与项目的交互数据中学习仪器变量表示.
- 在推系统中使用的图形卷积网络 (GCN) 中解决偏差放大问题.
主要方法:
- 在推系统 (DIVRS) 中开发数据驱动的IV表示学习,以将用户行为分解为因果关系和混关系.
- 引入了正交促进调整 (OPR) 和DIVRS特定的GCN变体 (DIVRS-GCN) 以减轻偏差放大.
主要成果:
- DIVRS和DIVRS-GCN有效地减轻了推系统中的混偏差.
- 这两种算法在Douban-Movie和Movielens-10M数据集上表现出优异的性能,提高了Recall@20的高达10.98%.
结论:
- 拟议的DIVRS和DIVRS-GCN方法为推系统提供了强大而有效的解决方案.
- 这些方法提高了推的准确性,多样性和平衡性,克服了现有的基于IV的系统的局限性.
更多相关视频
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
08:27Applying an eMASS Customization Program as a Research Tool to Evaluate Consumer Benefits
Published on: September 27, 2019
相关概念视频
Hindsight Biases
Decision Making: P-value Method
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim is also stated. These statements can act as null and alternative hypotheses: a null hypothesis would be a neutral statement while the alternative hypothesis can...
Confirmation Biases
Regression Toward the Mean
Decision Making: Traditional Method
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
Randomized Experiments
Simple randomization
Simple...