摘要
序列推荐系统(sequential recommendation system,SRS)旨在基于用户的历史行为偏好预测下一步行为.尽管针对序列推荐提出了许多有效的方法,但仍然存在根本性的挑战.首先,随着在线服务的普及,推荐系统需要同时服务于热启动用户和冷启动用户.然而,由于难以从交互数据有限的序列中学习到有效的序列依赖关系,大多数依赖于用户-项目交互的现有模型失去了优势.其次,由于现实中用户意图的可变性和主观随机性,用户在其历史序列中的行为往往是隐含和复杂的,很难从这些用户-项目交互数据中捕获这种动态转变模式.提出了一种基于图插值和可变形卷积网络的序列推荐(graph-based interpolation sequential recommender with deformable convolutional network,GISDCN)模型.对于冷启动用户,将序列对象重新构建成图,并提取全局序列中的知识来推断用户可能的偏好.为了捕捉复杂的顺序依赖关系,使用可变形卷积网络来生成更健壮和灵活的卷积核.最后,在4个数据集上进行了综合实验,验证了模型的有效性.实验结果表明,GISDCN优于大多数主流的模型.
Sequential recommendation systems aim to predict users’next actions based on the preferences learned from their historical behaviors.There are still fundamental challenges for sequential recommender.First,with the popularization of online services,recommender need serve both the warm-start and cold-start users.However,the most existing models depending on user-item interactions lose merits due to the difficulty of learning sequential dependencies with limited interactions.Second,users’behaviors in their historical sequences are often implicit and complex due to the objective variability of reality and the subjective randomness of users’intentions.It is difficult to capture the dynamic transition patterns from these user-item interactions.In this work,we propose a graph-based interpolation sequential recommender with deformable convolutional network(GISDCN).For cold-start users,we reconstruct item sequences into a graph to infer users’possible preferences.To capture the complex sequential dependencies,we employ the deformable convolutional network to generate more robust and flexible filters.Finally,we conduct comprehensive experiments and verify the effectiveness of our model.The experimental results demonstrate that GISDCN outperforms most of the state-of-the-art models at cold-start conditions.
作者
刘昕悦
尹海莲
臧亚磊
吴文隆
卓俊男
徐凤如
陈吕莹
马维华
李博涵
Liu Xinyue;Yin Hailian;Zang Yalei;Wu Wenlong;Zhuo Junnan;Xu Fengru;Chen lüying;Ma Weihua;and Li Bohan(College of Artificial Intelligence,Nanjing University of Aeronautics and Astronautics,Nanjing 211106;Key Laboratory of Brain-Machine Intelligence Technology(Nanjing University of Aeronautics and Astronautics),Ministry of Education,Nanjing 211106;Key Laboratory of Collaborative Innovation Center of Novel Software Technology and Industrialization,Nanjing 211106;Key Laboratory of Advanced Technology for Small and Medium-sized UAVs(Nanjing University of Aeronautics and Astronautics),Ministry of Industry and Information Technology,Nanjing 210006;College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016)
出处
《计算机研究与发展》
北大核心
2025年第10期2583-2594,共12页
Journal of Computer Research and Development
基金
国家自然科学基金项目(U23B2057,62176185)
南京航空航天大学研究生教育教学改革专项项目(卓越工程师)(2024YJXGG-Z12)
南京航空航天大学实践创新项目(xcxjh20221605)
江苏省研究生科研与实践创新计划(KYCX25_0645)。
关键词
序列推荐
可变形卷积
图神经网络
冷启动
动态卷积
sequential recommendation(SR)
deformable convolution
graph neural network
cold-start
dynamic convolution
