与仅具有节点成对关系的普通网络不同,超网络的节点之间还存在复杂的元组关系,即,超边。而现有的大多数网络表示学习方法不能有效地捕获复杂的元组关系。针对上述问题,该文提出一种基于平移约束的异质超网络表示学习方法(HRTC)。首先,该方法结合团扩展和星型扩展将抽象为超图的异质超网络转换为抽象为2-截图+关联图的异质网络。然后,提出一种感知节点语义相关性的元路径游走方法来捕获节点之间的语义关系。最后,在训练节点成对关系的同时,通过引入知识表示学习中的平移机制来捕获节点之间的元组关系。实验结果表明,对于链接预测任务,该方法的性能接近于其他最优基线方法;对于超网络重建任务,当超边重建比率大于0.6时,该方法在drug数据集上的性能优于其他最优基线方法,同时该方法在GPS数据集上的平均性能超过其他最优基线方法16.24%。
Abstract
In contrast to the ordinary network with only pairwise relationships between the nodes, there also exist complex tuple relationships (i.e. the hyperedges) among the nodes in the hypernetwork. However, most of the existing network representation learning methods cannot effectively capture complex tuple relationships. Therefore, to resolve this issue, a heterogeneous hypernetwork representation learning method with the translation constraint (HRTC) is proposed. Firstly, the proposed method combines clique expansion and star expansion to transform a heterogeneous hypernetwork abstracted as the hypergraph into a heterogeneous network abstracted as 2-section graph+incidence graph. Secondly, a meta-path walk method aware of semantic relevance of the nodes (SRwalk) is proposed to capture semantic relationships between the nodes. Finally, while the pairwise relationships between the nodes are trained, the tuple relationships among the nodes are captured by introducing the translation mechanism in knowledge representation learning. Experimental results show that as for the link prediction task, the performance of the proposed method is close to that of other optimal baseline methods, and as for the hypernetwork reconstruction task, the performance of the proposed method is better than that of other optimal baseline methods on the drug dataset for case beyond 0.6 hyperedge reconstruction ratio, meanwhile, the average performance of the proposed method outperforms that of other optimal baseline methods by 16.24% on the GPS dataset.
关键词
网络表示学习 /
超网络结构 /
平移约束 /
链接预测 /
超网络重建
{{custom_keyword}} /
Key words
network representation learning /
hypernetwork structure /
translation constraint /
link prediction /
hypernetwork reconstruction
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王岩,唐杰. 网络表示学习算法的分析与验证[J]. 中文信息学报,2019,33 (2): 97-104.
[2] 吴越,王英,王鑫,等. 基于超图卷积的异质网络半监督节点分类[J]. 计算机学报,2021,44(11): 2248-2260.
[3] 张宁豫,陈曦,陈矫彦,等. 基于位置的知识图谱链接预测[J]. 中文信息学报,2018,32(4): 80-86,129.
[4] 蒋盛益,杨博泓,姚娟娜,等. 一种基于增广网络的快速微博社区检测算法[J]. 中文信息学报,2016,30(5): 65-72.
[5] 胡秉德,王新根,王新宇,等. 超图学习综述:算法分类与应用分析[J]. 软件学报,2022,33(2): 498-523.
[6] Agarwal S,Branson K,Belongie S. Higher order learning with graphs[C]//Proceedings of the 23rd International Conference on Machine Learning,2006: 17-24.
[7] Huang J,Chen C,Ye F H,et al. Hyper2Vec: Biased random walk for hyper-network embedding[C]//Proceedings of the International Conference on Database Systems for Advanced Applications,2019: 273-277.
[8] Huang J,Liu X,Song Y Q. Hyper-path-based representation learning for hyper-networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management,2019: 449-458.
[9] Tu K,Cui P,Wang X,et al. Structural deep embedding for hypernetworks[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence,2018: 426-433.
[10] Mikolov T,Sutskever I,Chen Kai,et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of International Conference on Neural Information Processing Systems,2013: 3111-3119.
[11] 郑玉艳,王明省,石川,等. 异质信息网络中基于元路径的社团发现算法研究[J]. 中文信息学报,2018,32(9): 132-142.
[12] Bretto A. Hypergraph theory: An introduction[M]. Cham: Springer,2013.
[13] Bordes A,Usunier N,Garciaduran A. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems,2013: 2787-2795.
[14] Zheng V W,Cao B,Zheng Y,et al. Collaborative filtering meets mobile recommendation: A user-centered approach[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence,2010: 236-241.
[15] Harper F M,Konstan J A. The movielens datasets: History and context[J]. Ksii Transactions on Internet and Information Systems,2016,5(4):19.
[16] Perozzi B,Al-Rfou R,Skiena S.Deepwalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2014: 701-710.
[17] Grover A,Leskovec J.Node2Vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016: 855-864.
[18] Dong Y X,Chawla N V,Swami A.Metapath2Vec: Scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2017: 135-144.
[19] Fu G,Yuan B,Duan Q,et al. Representation learning for heterogeneous information networks via embedding events[C]//Proceedings of the International Conference on Neural Information Processing,2019: 327-339.
[20] 姜正申,刘宏志,付彬,等. 集成学习的泛化误差和AUC分解理论及其在权重优化中的应用[J].计算机学报,2019,42(1): 1-15.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62166032,62162053,62062059);青海省自然科学基金(2022-ZJ-961Q)
{{custom_fund}}
PDF(2609 KB)
