近些年,网络表示学习问题吸引了大量研究者的关注,而异构信息网络由于其丰富的结构语义信息及其广阔的应用领域,更是成为了网络表示学习领域的重中之重。目前面向异构信息网络的表示学习模型主要可以分为基于生成式模型的表示学习方法和基于判别式模型的表示学习方法,但是很少有工作同时结合两种模型进行表示学习的优化。该文提出了结合生成式模型和判别式模型的异构信息网络表示学习模型HINGAN,主要是将对抗生成思想融入异构信息网络表示学习过程中,达到优化网络表示结果的目的。该模型首先在元路径的引导下构建带权信息网络图,然后在带权图上计算更新构造的生成器和判别器参数,通过生成对抗的博弈思想来获取最大收益。在AMiner和DBLP两个真实学术图谱数据集上的实验结果表明,HINGAN在多标签分类、链路预测以及可视化方面都能比现在主流的网络表示方法取得更优的效果,并且HINGAN可以应用于大规模的异构网络数据的表示和计算。除此之外,该文还总结了已有研究成果并对未来研究可能面临的挑战进行了展望。
Abstract
Due to the abundant structural and semantic information in the heterogeneous information network as well as its wide application, network representation learning for heterogeneous information networks has become a vital research issue. The current representation learning models for heterogeneous information network can be divided into generative model based or discriminative model based methods. In this paper, we propose a representation learning model for the heterogeneous information network called HINGAN, which integrates the generative adversarial network into the representation learning process of heterogeneous information network to improve network representational outcomes. Firstly, this model builds a weighted homogeneous information network in the guidance of the meta-path. Then, by employing the GAN for the greatest gain, it updates parameters of the constructed generator and discriminator on the weighted network. According to the experimental results on AMiner and DBLP, HINGAN can get a more outstanding effect than present mainstream network representation methods from the aspects of multi-label classification and visualization. At the same time, HINGAN can be applied to extensively scalable representation and effective calculation of the heterogeneous network data.
关键词
异质信息网络 /
语义信息挖掘 /
生成对抗网络 /
语义关系预测
{{custom_keyword}} /
Key words
heterogeneous information network /
semantic information mining /
generative adversarial netwrok /
link prediction
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 涂存超,杨成,刘知远,等.网络表示学习综述[J].中国科学:信息科学,2017,52(52):1412.
[2] 齐金山,梁循,李志宇,等.大规模复杂信息网络表示学习:概念,方法与挑战[J].计算机学报,2017:1-26.
[3] 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.ACM,2014:701-710.
[4] 温雯,黄家明,蔡瑞初,等.一种融合节点先验信息的图表示学习方法[J].软件学报,2018,3:786-798.
[5] 陈丽,朱裴松,钱铁云,等.基于边采样的网络表示学习模型[J].软件学报,2018,3:756-771.
[6] Belkin M,Niyogi P.Laplacian eigenmaps and spectral techniques for embedding and clustering[C]//Proceedings of Advances in Neural Information Processing Systems.2002:585-591.
[7] 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.ACM,2016:855-864.
[8] Tang J,Qu M,Wang M,et al.Line: Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.International World Wide Web Conferences Steering Committee,2015:1067-1077.
[9] Cao S,Lu W,Xu Q.Grarep:Learning graph representations with global structural information[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.ACM,2015:891-900.
[10] Wang D,Cui P,Zhu W.Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:1225-1234.
[11] Sun Y,Han J.Mining heterogeneous information networks:Principles and methodologies[J].Synthesis Lectures on Data Mining and Knowledge Discovery,2012,3(2):1-159.
[12] Wang H,Wang J.GraphGAN:Graph representation learning with generative adversarial nets[J].arXiv preprint arXiv:1711.08267,2017.
[13] Dai Q,Li Q,Tang J,et al.Adversarial network embedding[J].arXiv preprint arXiv:1711.07838,2017.
[14] Shi C,Hu B,Zhao W X,et al.Heterogeneous information network embedding for recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2019,31(2):357-370.
[15] Dong Y,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.ACM,2017:135-144.
[16] Tan H,Tang W,Fan X,et al.SERL:Semantic-path biased representation learning of heterogeneous information network[C]//Proceedings of the Knowledge Science,Engineering and Management,2018:287-298.
[17] Mikolov T,Sutskever I,Chen K,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of Advances in Neural Information Processing Systems.2013:3111-3119.
[18] Fu T,Lee W C,Lei Z.Hin2vec:Explore meta-paths in heterogeneous information networks for representation learning[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.ACM,2017:1797-1806.
[19] Chang S,Han W,Tang J,et al.Heterogeneous network embedding via deep architectures[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:119-128.
[20] Cai X,Han J,Yang L.Generative adversarial network based heterogeneous bibliographic network representation for personalized citation recommendation[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence,2018:5747-5754.
[21] Tang J,Zhang J,Yao L,et al.Arnetminer:Extraction and mining of academic social networks[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2008:990-998.
[22] Maaten L,Hinton G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9:2579-2605.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研发计划(2017YFC0820700);国家自然科学基金(61472403)
{{custom_fund}}
PDF(4666 KB)
