Multi-behavior recommendation exploits multiple types of user-item interactions, such asviewandcart, to learn user preferences and has demonstrated to be an effective solution to alleviate the data sparsity problem faced by the traditional models that often utilize only one type of interaction for recommendation. In real scenarios, users often take a sequence of actions to interact with an item, in order to get more information about the item and thus accurately evaluate whether an item fits their personal preferences. Those interaction behaviors often obey a certain order, and more importantly, different behaviors reveal different information or aspects of user preferences towards the target item. Most existing multi-behavior recommendation methods take the strategy to first extract information from different behaviors separately and then fuse them for final prediction. However, they have not exploited the connections between different behaviors to learn user preferences. Besides, they often introduce complex model structures and more parameters to model multiple behaviors, largely increasing the space and time complexity. In this work, we propose a lightweight multi-behavior recommendation model namedCascading Residual Graph Convolutional Network(CRGCNfor short) for multi-behavior recommendation, which can explicitly exploit the connections between different behaviors into the embedding learning process without introducing any additional parameters (with comparison to the single-behavior based recommendation model). In particular, we design a cascading residualgraph convolutional network (GCN)structure, which enables our model to learn user preferences by continuously refining the embeddings across different types of behaviors. The multi-task learning method is adopted to jointly optimize our model based on different behaviors. Extensive experimental results on three real-world benchmark datasets show that CRGCN can substantially outperform the state-of-the-art methods, achieving 24.76%, 27.28%, and 25.10% relative gains on average in terms of HR@K (K = {10,20,50,80}) over the best baseline across the three datasets. Further studies also analyze the effects of leveraging multi-behaviors in different numbers and orders on the final performance.

Mingshi Yan

Zhiyong Cheng

Chen Gao

Jing Sun

Fan Liu

Fuming Sun

Haojie Li

ACM Transactions on Information Systems

ACM 信息系统交易 (TOIS) 发表有关信息检索（例如搜索引擎、推荐系统）的论文，其中包含：具有良好经验验证的新的原则性信息检索模型或算法；观察、实验和/或理论研究产生新的见解信息检索或信息搜索；现有信息检索技术的应用说明，阐明了这些技术的优缺点；新的信息检索或信息搜索任务的形式化以及评估这些任务性能的方法；内容的开发（文本、图像、语音、视频等）支持信息检索和信息搜索的分析方法；开发用户信息偏好和交互行为的计算模型；创建和分析信息检索和信息搜索的评估方法； ACM TRANSACTIONS ON INFORMATION SYSTEMS (TOIS) 的信息检索范围因其丰富的创意而吸引了行业从业者，并因其对同事工作的描述而吸引了学术研究人员。

ACM Transactions on Information Systems publishes research papers on information retrieval, such as search engines and recommendation systems. The content includes: well-validated new principled models or algorithms for information retrieval; new insights generated from observational, experimental, and theoretical studies; application examples of existing information retrieval technologies, highlighting their advantages and disadvantages; formalization of new information retrieval or search tasks and methods for evaluating their performance; analytical methods supporting content development (text, images, speech, video, etc.) for information retrieval and search; computational models of user information preferences and interaction behaviors; and the creation and analysis of evaluation methods for information retrieval and search. Due to its rich creativity and in-depth descriptions of peer work, ACM Transactions on Information Systems attracts the attention of both industry practitioners and academic researchers.

《ACM Transactions on Information Systems》发表有关信息检索（如搜索引擎、推荐系统）的研究论文。内容包括：经过良好经验验证的新信息检索模型或算法；通过观察、实验和理论研究获得的新见解；现有信息检索技术的应用示例，阐述其优缺点；新信息检索或信息搜索任务的形式化及其性能评估方法；支持信息检索和搜索的内容开发（文本、图像、语音、视频等）分析方法；用户信息偏好和交互行为的计算模型；信息检索和搜索评估方法的创建与分析。由于其丰富的创意和对同行研究的深入描述，《ACM Transactions on Information Systems》吸引了行业从业者和学术研究人员的关注。

Category	Quartile
计算机科学	2
计算机科学, 计算机信息系统	2

Cascading Residual Graph Convolutional Network for Multi-Behavior Recommendation

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info