鉴于传统的异质信息网络通常存在的高维稀疏性缺点，首先提出将异质信息网络的高维顶点嵌入低维向量空间的无监督学习模型——基于生成对抗网络的异质网络表征学习（heterogeneous network representation learning based on generative adversarialnetwork，HNRL-GAN）模型；然后分析HNRL-GAN模型中的不足之处，进一步提出改进后的基于生成对抗网络的增强版异质网络表征学习（heterogeneous network representationlearning based on generative adversarial network plus plus，HNRL-GAN++）模型；最后分别在DBLP、Yelp、Aminer等数据集中使用HNRL-GAN模型和HNRL-GAN++模型进行节点分类和节点聚类等实验以测试模型的有效性。实验结果表明：1）HNRL-GAN模型和HNRL-GAN++模型都实现了将异质信息网络中的高维稀疏节点表示为低维稠密向量这一目标；2）相较于HNRL-GAN模型，HNRL-GAN++模型在保留高维空间中网络结构信息和语义信息等方面拥有更好的性能。
In view of the high-dimensional sparsity shortcomings of traditional heterogeneous information networks, we firstly proposed an unsupervised learning model-heterogeneous network representation learning based on generative adversarial network (HNRL-GAN) that embeds the high-dimensional vertices of heterogeneous information networks into low-dimensional vector spaces. Secondly, having analyzed the shortcomings of HNRL-GAN, we proposed an improved model, called as heterogeneous network representation learning based on generative adversarial network plus plus (HNRL-GAN++). Finally, we used HNRL-GAN and HNRL-GAN++ in three data sets, including DBLP, Yelp, and Aminer, to perform node classification and node clustering for testing the effectiveness of the two models. Experimental results show that: 1) Both HNRL-GAN and HNRL-GAN++ achieve the goal of representing high-dimensional sparse nodes in heterogeneous information networks as low-dimensional dense vectors; 2) Compared with HNRL-GAN, HNRL-GAN++ has better performance in retaining network structure information and semantic information in high-dimensional space.
[1] Sun Y, Han J. Mining heterogeneous information networks:a structural analysis approach[J]. ACM SIGKDD Explorations News Letter, 2013, 14(2):20-28.
[2] Sun Y, Norick B, Han J, et al. Integrating meta-path selection with user-guided object clustering in heterogeneous information networks[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY:ACM Press, 2012:1348-1356.
[3] Kong X, Yu P S, Ding Y, et al. Meta path-based collective classification in heterogeneous information networks[C]//Proceedings of the ACM International Conference on Information and Knowledge Management. New York, NY:ACM Press, 2012:1567-1571.
[4] Cao B, Kong X, Yu P S. Collective prediction of multiple types of links in heterogeneous information networks[C]//Proceedings of the IEEE International Conference on Data Mining. Piscataway, NJ:IEEE Press, 2015:50-59.
[5] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J/OL]. arXiv preprint arXiv:1406.2661, 2014. (2014-06-10)[2020-06-10]. https://arxiv.org/abs/1406.2661.
[6] Wang H, Wang J. GraphGAN:graph representation learning with generative adversarial nets[J/OL]. arXiv preprint arXiv:1711.08267, 2017. (2017-11-22)[2020-06-10]. https://arxiv.org/abs/1711.08267.
[7] 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. New York, NY:ACM Press, 2017:135-144.
[8] Shang J, Qu M, Liu J, et al. Meta-path guided embedding for similarity search in large-scale heterogeneous information networks[J/OL]. arXiv preprint arXiv:1610.09769, 2016. (2016-10-31)[2020-06-10]. https://arxiv.org/abs/1610.09769.
[9] Xu L, Wei X, Cao J, et al. Embedding of embedding (EOE):joint embedding for coupled heterogeneous networks[C]//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. New York, NY:ACM Press, 2017:741-749.
[10] Fu T, Lee W C, Lei Z. HIN2Vec:explore meta-paths in heterogeneous information networks for representation learning[C]//Proceedings of the 26th ACM International Conference on Information and Knowledge Management. New York, NY:ACM Press, 2017:1797-1806.
[11] Wang H, Zhang F, Hou M, et al. SHINE:signed heterogeneous information network embedding for sentiment link prediction[J/OL]. arXiv preprint arXiv:1712.00732, 2017. (2017-12-03)[2020-06-10]. https://arxiv.org/abs/1712.00732.
[12] Cai X, Han J, Yang L. Generative adversarial network based heterogeneous bibliographic network representation for personalized citation recommendation[C]//AAAI Conference on Artificial Intelligence. Palo Alto, CA:AAAI Press, 2018:5747-5754.
[13] Dai Q, Li Q, Tang J, et al. Adversarial network embedding[OL]. arXiv preprint arXiv:1711.07838, 2017. (2017-11-21)[2020-06-10]. https://arxiv.org/abs/1711.07838.
[14] Yu W, Zheng C, Cheng W, et al. Learning deep network representations with adversarially regularized autoencoders[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY:ACM Press, 2017:2663-2671.
[15] Pan S, Hu R, Long G, et al. Adversarially regularized graph autoencoder for graph embedding[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Sacramento, CA:IJCAI Press, 2018:2609-2615.
[16] Hu B, Fang Y, Shi C. Adversarial learning on heterogeneous information networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY:ACM Press, 2019:120-129.
