A Novel Popularity Extraction Method Applied in Session-Based Recommendation  

作　　者：Yuze Peng Shengjun Xu Qingkun Chen Wenjin Huang Yihua Huang 

机构地区：[1]School of Electronics and Information Technology,Sun Yat-sen University,Guangzhou 510006,China [2]Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems,Sun Yat-sen University,Guangzhou 510006,China,and Southern Marine Science and Engineering Guangdong Laboratory,Zhuhai 519080,China

出　　处：《Tsinghua Science and Technology》2024年第4期971-984,共14页清华大学学报自然科学版（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.62276278);Guangdong Basic and Applied Basic Research Foundation(No.2022A1515110006).

摘　　要：Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regardless of the previous trends of this ratio or metric and the attribute diversity of items. To solve this problem and reach accurate popularity, we creatively propose to extract the popularity of an item according to the Proportional Integral Differential (PID) idea. Specifically, Integral (I) integrates a physical quantity over a time window, which agrees with the fact that determining the attributes of items also requires a long-term observation. The Differential (D) emphasizes an incremental change of a physical quantity over time, which coincidentally caters to a trend. Moreover, in the Session-Based Recommendation (SBR) community, many methods extract session interests without considering the impact of popularity on interest, leading to suboptimal recommendation results. To further improve recommendation performance, we propose a novel strategy that leverages popularity to enhance the session interest (popularity-aware interest). The proposed popularity by PID is further used to construct the popularity-aware interest, which consistently improves the recommendation performance of the main models in the SBR community. For STAMP, SRGNN, GCSAN, and TAGNN, on Yoochoose1/64, the metric P@20 is relatively improved by 0.93%, 1.84%, 2.02%, and 2.53%, respectively, and MRR@20 is relatively improved by 3.74%, 1.23%, 2.72%, and 3.48%, respectively. On Movieslen-1m, the relative improvements of P@20 are 7.41%, 15.52%, 8.20%, and 20.12%, respectively, and that of MRR@20 are 2.34%, 12.41%, 20.34%, and 19.21%, respectively.

关 键 词：POPULARITY Proportional Integral Differential(PID) algorithm session-based recommendation user’s interests 

分 类 号：TP316[自动化与计算机技术—计算机软件与理论] TP309[自动化与计算机技术—计算机科学与技术]