Page 398 - 《软件学报》2024年第6期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2024,35(6):2974−2998 [doi: 10.13328/j.cnki.jos.006915] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

*
融合自适应周期与兴趣量因子的轻量级 GCN 推荐

钱忠胜, 叶祖铼, 姚昌森, 张 丁, 黄 恒, 秦朗悦

(江西财经大学 信息管理学院, 江西 南昌 330013)
通信作者: 钱忠胜, E-mail: changesme@163.com

摘 要: 推荐系统在成熟的数据挖掘技术推动下, 已能高效地利用评分数据、行为轨迹等显隐性信息, 再与复杂而
先进的深度学习技术相结合, 取得了很好的效果. 同时, 其应用需求也驱动着对基础数据的深度挖掘与利用, 以及
对技术要求的减负成为一个研究热点. 基于此, 提出一种利用 GCN (graph convolutional network) 方法进行深度信
息融合的轻量级推荐模型 LG_APIF. 该模型结合行为记忆, 通过艾宾浩斯遗忘曲线模拟用户兴趣变化过程, 采用线
性回归等相对轻量的传统方法挖掘项目的自适应周期等深度信息; 分析用户当前的兴趣分布, 计算项目的兴趣量,
以获取用户的潜在兴趣类型; 构建用户-类型-项目三元组的图结构, 并结合减负后的 GCN 技术来生成最终的项目
推荐列表. 实验验证所提方法的有效性, 通过与 8 个经典模型在 Last.fm, Douban, Yelp, MovieLens 数据集中的对
比, 表明该方法在 Precision, Recall 及 NDCG 指标上都得到良好改善, 其中, Precision 平均提升 2.11%, Recall 平均
提升 1.01%, NDCG 平均提升 1.48%.
关键词: 行为记忆; 自适应周期; 兴趣量因子; 图卷积网络; 推荐系统
中图法分类号: TP311

中文引用格式: 钱忠胜, 叶祖铼, 姚昌森, 张丁, 黄恒, 秦朗悦. 融合自适应周期与兴趣量因子的轻量级GCN推荐. 软件学报, 2024,
35(6): 2974–2998. http://www.jos.org.cn/1000-9825/6915.htm
英文引用格式: Qian ZS, Ye ZL, Yao CS, Zhang D, Huang H, Qin LY. Lightweight GCN Recommendation Combining Adaptive
Period and Interest Factor. Ruan Jian Xue Bao/Journal of Software, 2024, 35(6): 2974–2998 (in Chinese). http://www.jos.org.cn/1000-
9825/6915.htm

Lightweight GCN Recommendation Combining Adaptive Period and Interest Factor

QIAN Zhong-Sheng, YE Zu-Lai, YAO Chang-Sen, ZHANG Ding, HUANG Heng, QIN Lang-Yue
(School of Information Management, Jiangxi University of Finance & Economics, Nanchang 330013, China)
Abstract: Driven by mature data mining technologies, the recommendation system has been able to efficiently utilize explicit and implicit
information such as score data and behavior traces and then combine the information with complex and advanced deep learning
technologies to achieve sound results. Meanwhile, its application requirements also drive the in-depth mining and utilization of basic data
and the load reduction of technical requirements to become research hotspots. On this basis, a lightweight recommendation model, namely
LG_APIF is proposed, which uses the graph convolutional network (GCN) method to deeply integrate information. According to behavior
memory, the model employs Ebbinghaus forgetting curve to simulate the users’ interest change process and adopts linear regression and
other relatively lightweight traditional methods to mine adaptive periods and other depth information of items. In addition, it analyzes users’
current interest distribution and calculates the interest value of the item to obtain users’ potential interest type. It further constructs the
graph structure of the user-type-item triplet and uses GCN technology after load reduction to generate the final item recommendation list.
The experiments have verified the effectiveness of the proposed method. Through the comparison with eight classical models on the
datasets of Last.fm, Douban, Yelp, and MovieLens, it is found that the Precision, Recall, and NDCG of the proposed method are
improved, with an average improvement of 2.11% on Precision, 1.01% on Recall, and 1.48% on NDCG, respectively.
Key words: behavior memory; adaptive period; interest factor; graph convolutional network (GCN); recommendation system

* 基金项目: 国家自然科学基金 (62262025); 江西省自然科学基金重点项目 (20224ACB202012)
收稿时间: 2022-06-18; 修改时间: 2022-10-27; 采用时间: 2023-02-07; jos 在线出版时间: 2023-08-09
CNKI 网络首发时间: 2023-08-10