ABSTRACT
Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes. However, commonly do GCNs focus more on node features but less on graph structures within the neighborhood, especially higher-order structural patterns. However, such local structural patterns are shown to be indicative of node properties in numerous fields. In addition, it is not just single patterns, but the distribution over all these patterns matter, because networks are complex and the neighborhood of each node consists of a mixture of various nodes and structural patterns. Correspondingly, in this paper, we propose Graph Structural topic Neural Network, abbreviated GraphSTONE 1, a GCN model that utilizes topic models of graphs, such that the structural topics capture indicative graph structures broadly from a probabilistic aspect rather than merely a few structures. Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently. In addition, we design multi-view GCNs to unify node features and structural topic features and utilize structural topics to guide the aggregation. We evaluate our model through both quantitative and qualitative experiments, where our model exhibits promising performance, high efficiency, and clear interpretability.
Supplemental Material
- Sanjeev Arora, Rong Ge, Yonatan Halpern, David Mimno, Ankur Moitra, David Sontag, Yichen Wu, and Michael Zhu. 2013. A practical algorithm for topic modeling with provable guarantees. In International Conference on Machine Learning. 280--288.Google ScholarDigital Library
- Sanjeev Arora, Rong Ge, and Ankur Moitra. 2012. Learning topic models--going beyond SVD. In 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science. IEEE, 1--10.Google ScholarDigital Library
- DavidMBlei, AndrewY Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022.Google ScholarDigital Library
- Karsten M Borgwardt and Hans-Peter Kriegel. 2005. Shortest-path kernels on graphs. In Fifth IEEE international conference on data mining. IEEE, 8--pp.Google ScholarDigital Library
- Claire Donnat, Marinka Zitnik, David Hallac, and Jure Leskovec. 2018. Learning structural node embeddings via diffusion wavelets. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1320--1329.Google ScholarDigital Library
- Mark S Granovetter. 1977. The strength of weak ties. In Social networks. Elsevier, 347--367.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. 1024--1034.Google Scholar
- Sergey Ivanov and Evgeny Burnaev. 2018. Anonymous Walk Embeddings. In International Conference on Machine Learning. 2191--2200.Google Scholar
- Di Jin, Xinxin You, Weihao Li, Dongxiao He, Peng Cui, Françoise Fogelman- Soulié, and Tanmoy Chakraborty. 2019. Incorporating network embedding into markov random field for better community detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 160--167.Google ScholarDigital Library
- Yilun Jin, Guojie Song, and Chuan Shi. 2020. GraLSP: Graph Neural Networks with Local Structural Patterns. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, New York, NY, USA. AAAI Press, 4361--4368.Google Scholar
- Noriaki Kawamae. 2019. Topic Structure-Aware Neural Language Model: Unified language model that maintains word and topic ordering by their embedded representations. In The World Wide Web Conference. ACM, 2900--2906.Google ScholarDigital Library
- Thomas Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference of Learning Representations.Google Scholar
- Danai Koutra, U Kang, Jilles Vreeken, and Christos Faloutsos. 2014. Vog: Summarizing and understanding large graphs. In Proceedings of the 2014 SIAM international conference on data mining. SIAM, 91--99.Google ScholarCross Ref
- Daniel D Lee and H Sebastian Seung. 1999. Learning the parts of objects by non-negative matrix factorization. Nature 401, 6755 (1999), 788.Google Scholar
- John Boaz Lee, Ryan A Rossi, Xiangnan Kong, Sungchul Kim, Eunyee Koh, and Anup Rao. 2019. Graph Convolutional Networks with Motif-based Attention. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 499--508.Google ScholarDigital Library
- Ziyao Li, Liang Zhang, and Guojie Song. 2019. GCN-LASE: towards adequately incorporating link attributes in graph convolutional networks. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press, 2959--2965.Google ScholarCross Ref
- Lin Liu, Lin Tang, Libo He, Shaowen Yao, and Wei Zhou. 2017. Predicting protein function via multi-label supervised topic model on gene ontology. Biotechnology & Biotechnological Equipment 31, 3 (2017), 630--638.Google ScholarCross Ref
- Yang Liu, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun. 2015. Topical word embeddings. In Twenty-Ninth AAAI Conference on Artificial Intelligence.Google ScholarDigital Library
- Qingqing Long, Yiming Wang, Lun Du, Guojie Song, Yilun Jin, andWei Lin. 2019. Hierarchical Community Structure Preserving Network Embedding: A Subspace Approach. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 409--418.Google ScholarDigital Library
- Andreas Loukas. 2020. What graph neural networks cannot learn: depth vs width. In International Conference on Learning Representations. https://openreview.net/ forum?id=B1l2bp4YwSGoogle Scholar
- Silvio Micali and Zeyuan Allen Zhu. 2016. Reconstructing markov processes from independent and anonymous experiments. Discrete Applied Mathematics 200 (2016), 108--122.Google ScholarDigital Library
- Ron Milo, Shai Shen-Orr, Shalev Itzkovitz, Nadav Kashtan, Dmitri Chklovskii, and Uri Alon. 2002. Network motifs: simple building blocks of complex networks. Science 298, 5594 (2002), 824--827.Google Scholar
- Christopher Morris, Martin Ritzert, Matthias Fey, William L Hamilton, Jan Eric Lenssen, Gaurav Rattan, and Martin Grohe. 2019. Weisfeiler and leman go neural: Higher-order graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 4602--4609.Google ScholarDigital Library
- Kenta Oono and Taiji Suzuki. 2020. Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. In International Conference on Learning Representations. https://openreview.net/forum?id=S1ldO2EFPrGoogle Scholar
- Leonardo FR Ribeiro, Pedro HP Saverese, and Daniel R Figueiredo. 2017. struc2vec: Learning node representations from structural identity. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 385--394.Google ScholarDigital Library
- Nino Shervashidze, SVN Vishwanathan, Tobias Petri, Kurt Mehlhorn, and Karsten Borgwardt. 2009. Efficient graphlet kernels for large graph comparison. In Artificial Intelligence and Statistics. 488--495.Google Scholar
- Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Keyulu Xu,Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).Google Scholar
- Yizhou Zhang, Guojie Song, Lun Du, Shuwen Yang, and Yilun Jin. 2019. DANE: Domain Adaptive Network Embedding. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.Google ScholarCross Ref
- Lekui Zhou, Yang Yang, Xiang Ren, Fei Wu, and Yueting Zhuang. 2018. Dynamic network embedding by modeling triadic closure process. In Thirty-Second AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
Recommendations
Graph neural topic model with commonsense knowledge
AbstractTraditional topic models are based on the bag-of-words assumption, which states that the topic assignment of each word is independent of the others. However, this assumption ignores the relationship between words, which may hinder the ...
Highlights- Commonsense knowledge is used to capture the relationship between words.
- ...
Twitter Opinion Topic Model: Extracting Product Opinions from Tweets by Leveraging Hashtags and Sentiment Lexicon
CIKM '14: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge ManagementAspect-based opinion mining is widely applied to review data to aggregate or summarize opinions of a product, and the current state-of-the-art is achieved with Latent Dirichlet Allocation (LDA)-based model. Although social media data like tweets are ...
The dual-sparse topic model: mining focused topics and focused terms in short text
WWW '14: Proceedings of the 23rd international conference on World wide webTopic modeling has been proved to be an effective method for exploratory text mining. It is a common assumption of most topic models that a document is generated from a mixture of topics. In real-world scenarios, individual documents usually concentrate ...
Comments