用灰系统模型解决推荐系统冷启动与隐私问题
GreyShot: Zeroshot and Privacy-preserving Recommender System by GM(1,1) Model
- 基于GM(1,1)模型利用评分数据的泊松-帕累托特性
- 无需输入数据即可生成准确公平的推荐结果
- 适合关注隐私保护与零样本推荐的研究者
推荐系统构建中普遍面临冷启动问题。过去几十年，研究者多采用迁移学习和元学习方法应对。尽管近年出现如ZeroMat等例外方案，冷启动问题仍具挑战性。本文提出基于GM(1,1)模型的GreyShot算法，充分利用在线评分数据的泊松-帕累托特性，构建零样本且隐私保护的推荐系统。该方法无需任何输入数据，可有效生成准确且公平的推荐结果。结论表明，灰系统方法如GM(1,1)能有效解决推荐系统的零样本问题。
原文摘要 · Abstract (English)
Every recommendation engineer needs to face the cold start problem when building his system. During the past decades, most scientists adopted transfer learning and meta learning to solve the problem. Although notable exceptions such as ZeroMat etc. have been invented in recent years, cold-start problem remains a challenging problem for many researchers. In this paper, we build a zeroshot and privacy-preserving recommender system algorithm GreyShot using GM(1,1) model by taking advantage of the Poisson-Pareto property of the online rating data. Our approach relies on no input data and is effective in generating both accurate and fair results. In conclusion, zeroshot problem of recommender systems could be effectively solved by grey system methods such as GM(1,1).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。