摘要
为理解不同异构网络嵌入模型之间的差异,并解决评估异构网络嵌入模型所存在的定性分析复杂且隐藏的问题,对比分析方法首先应统一模型的评估指标和任务,然后训练模型以获取模型训练过程中的大量参数和特征信息,并保留完整且非均值化的评估结果进行可视化.基于模型参数和特征数据,设计并实现一个交互对比可视分析工具——HINCompare,包括基础评估指标的分布概览和推荐结果对比视图,以及模型嵌入过程中融合的局部拓扑结构特征视图.该工具支持探索模型中不同特征聚合方法所存在的共同模式和不同架构的模型之间的差异.此外,HINCompare通过热力图展示了用户在电影类型和年份上的偏好特征,可结合推荐结果的上下文信息进行分析和评估,解决推荐中的黑盒问题,提供推荐结果的来源信息,增加可解释性.最后,通过真实的豆瓣电影数据验证了系统的有效性.
To understand the differences between various heterogeneous information networks(HINs)em-bedding models,and to solve intricate and hidden problems in model evaluation,the comparative analysis method should include the following steps.First,the evaluation indicators and tasks are made consistent for all models.Then the parameters and structural features are extracted from the model training process and the complete and non-averaged evaluation results are retained for visualization.Based on the model parameters and characteristics data,we design and implement a visual analysis tool named HINCompare,which in-cludes an overview of the distribution of basic evaluation indicators,a comparison view of recommended re-sults,and a feature view of the local topology structure for model embedding.The tool allows developers to explore the common patterns of different feature aggregation methods of different models and the differ-ences in their architectures.In addition,HINCompare shows user’s preferences for movie types and years with heat maps,which are combined with the contextual information of the recommended results for further analysis and evaluation.The system provides insights into black-box problems of models and increases in-terpretability by supplying information about the sources of the results.We conduct the preliminary evalua-tion study with Douban movie data to verify the effectiveness of the system.
作者
王攸妍
汤颖
Wang Youyan;Tang Ying(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023)
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2021年第12期1821-1829,共9页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金面上项目(61972355)
浙江省公益技术研究计划(LGG19F020012).
关键词
可视分析
异构信息网络
异构网络嵌入模型
可解释性推荐
visual analysis
heterogeneous information network
heterogeneous network embedding model
in-terpretable recommendation
