Aravind Sankar
ABSTRACT
Heterogeneous Information Networks (HINs) comprise nodes of different types inter-connected through diverse semantic relationships. In many real-world applications, nodes in information networks are often associated with additional attributes, resulting in Attributed HINs (or AHINs). In this paper, we study semi-supervised learning (SSL) on AHINs to classify nodes based on their structure, node types and attributes, given limited supervision. Recently, Graph Convolutional Networks (GCNs) have achieved impressive results in several graph-based SSL tasks. However, they operate on homogeneous networks, while being completely agnostic to the semantics of typed nodes and relationships in real-world HINs.
In this paper, we seek to bridge the gap between semantic-rich HINs and the neighborhood aggregation paradigm of graph neural networks, to generalize GCNs through metagraph semantics. We propose a novel metagraph convolution operation to extract features from local metagraph-structured neighborhoods, thus capturing semantic higher-order relationships in AHINs. Our proposed neural architecture Meta-GNN extracts features of diverse semantics by utilizing multiple metagraphs, and employs a novel metagraph-attention module to learn personalized metagraph preferences for each node. Our semi-supervised node classification experiments on multiple real-world AHIN datasets indicate significant performance gains of 6% Micro-F1 on average over state-of-the-art AHIN baselines. Visualizations on metagraph attention weights yield interpretable insights into their relative task-specific importance.
- D. Zhou, O. Bousquet, T. N. Lal, J. Weston, and B. Schölkopf, "Learning with local and global consistency," in Advances in neural information processing systems, 2004, pp. 321--328.Google Scholar
- L. Tang and H. Liu, "Relational learning via latent social dimensions," in Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2009, pp. 817--826.Google Scholar
- A. Krishnan, A. Sharma, and H. Sundaram, "Improving latent user models in online social media," arXiv preprint arXiv.1711.11124, 2017.Google Scholar
- M. Ji, Y. Sun, M. Danilevsky, J. Han, and J. Gao, "Graph regularized transductive classification on heterogeneous information networks," in Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 2010, pp. 570--586.Google Scholar
- C. Yang, L. Bai, C. Zhang, Q. Yuan, and J. Han, "Bridging collaborative filtering and semi-supervised learning: a neural approach for poi recommendation," in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2017, pp. 1245--1254.Google Scholar
- A. Krishnan, A. Sharma, A. Sankar, and H. Sundaram, "An adversarial approach to improve long-tail performance in neural collaborative filtering," in Proceedings of the 27th ACM International Conference on Information and Knowledge Management, ser. CIKM '18. New York, NY, USA: ACM, 2018, pp. 1491--1494. [Online]. Available Google ScholarDigital Library
- Y. Sun, J. Han, X. Yan, P. S. Yu, and T. Wu, "Pathsim: Meta path-based top-k similarity search in heterogeneous information networks," Proceedings of the VLDB Endowment, vol. 4, no. 11, pp. 992--1003, 2011.Google ScholarDigital Library
- J. Atwood and D. Towsley, "Diffusion-convolutional neural networks," in Advances in Neural Information Processing Systems, 2016, pp. 1993--2001.Google Scholar
- T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," in International Conference for Learning Representations (ICLR), 2017.Google Scholar
- P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, "Graph attention networks," arXiv preprint arXiv:1710.10903, 2017.Google Scholar
- X. Li, Y. Wu, M. Ester, B. Kao, X. Wang, and Y. Zheng, "Semi-supervised clustering in attributed heterogeneous information networks," in Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2017, pp. 1621--1629.Google Scholar
- J. Hu, R. Cheng, K. C.-C. Chang, A. Sankar, Y. Fang, and B. Y. Lam, "Discovering maximal motif cliques in large heterogeneous information networks," in 2019 IEEE 35th International Conference on Data Engineering (ICDE). IEEE, 2019, pp. 746--757.Google Scholar
- D. Bahdanau, K. Cho, and Y. Bengio, "Neural machine translation by jointly learning to align and translate," arXiv preprint arXiv.1409.0473, 2014.Google Scholar
- M. Belkin, P. Niyogi, and V. Sindhwani, "Manifold regularization: A geometric framework for learning from labeled and unlabeled examples," Journal of machine learning research, vol. 7, no. Nov, pp. 2399--2434, 2006.Google ScholarDigital Library
- X. Zhou and M. Belkin, "Semi-supervised learning," in Academic Press Library in Signal Processing. Elsevier, 2014, vol. 1, pp. 1239--1269.Google Scholar
- B. Perozzi, R. Al-Rfou, and S. Skiena, "Deepwalk: Online learning of social representations," in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2014, pp. 701--710.Google Scholar
- A. Grover and J. Leskovec, "node2vec: Scalable feature learning for networks," in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2016, pp. 855--864.Google Scholar
- A. Sankar, A. Krishnan, Z. He, and C. Yang, "Rase: Relationship aware social embedding," in 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019.Google Scholar
- M. Henaff, J. Bruna, and Y. LeCun, "Deep convolutional networks on graph-structured data," CoRR, vol. abs/1506.05163, 2015.Google Scholar
- F. P. Such, S. Sah, M. Dominguez, S. Pillai, C. Zhang, A. Michael, N. Cahill, and R. Ptucha, "Robust spatial filtering with graph convolutional neural networks," arXiv preprint arXiv.1703.00792, 2017.Google Scholar
- W. Hamilton, Z. Ying, and J. Leskovec, "Inductive representation learning on large graphs," in Advances in Neural Information Processing Systems 30, 2017, pp. 1025--1035.Google Scholar
- A. Sankar, Y. Wu, L. Gou, W. Zhang, and H. Yang, "Dynamic graph representation learning via self-attention networks," arXiv preprint arXiv:1812.09430, 2018.Google Scholar
- Y. Dong, N. V. Chawla, and A. Swami, "metapath2vec: Scalable representation learning for heterogeneous networks," in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2017, pp. 135--144.Google Scholar
- H. Jiang, Y. Song, C. Wang, M. Zhang, and Y. Sun, "Semi-supervised learning over heterogeneous information networks by ensemble of meta-graph guided random walks." IJCAI, 2017.Google Scholar
- X. Kong, P. S. Yu, Y. Ding, and D. J. Wild, "Meta path-based collective classification in heterogeneous information networks," in Proceedings of the 21st ACM international conference on Information and knowledge management. ACM, 2012, pp. 1567--1571.Google Scholar
- T. Pham, T. Tran, D. Q. Phung, and S. Venkatesh, "Column networks for collective classification." in AAAI, 2017, pp. 2485--2491.Google Scholar
- Y. Fang, W. Lin, V. W. Zheng, M. Wu, K. C.-C. Chang, and X.-L. Li, "Semantic proximity search on graphs with metagraph-based learning," in Data Engineering (ICDE), 2016 IEEE 32nd International Conference on. IEEE, 2016, pp. 277--288.Google Scholar
- M. Wan, Y. Ouyang, L. Kaplan, and J. Han, "Graph regularized meta-path based transductive regression in heterogeneous information network," in Proceedings of the 2015 SIAM International Conference on Data Mining. SIAM, 2015, pp. 918--926.Google Scholar
- T.-y. Fu, W.-C. Lee, and Z. Lei, "Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning," in Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM, 2017, pp. 1797--1806.Google Scholar
- Y. Shi, H. Gui, Q. Zhu, L. Kaplan, and J. Han, "Aspem: Embedding learning by aspects in heterogeneous information networks," in Proceedings of the 2018 SIAM International Conference on Data Mining. SIAM, 2018, pp. 144--152.Google Scholar
- M. Latapy, "Main-memory triangle computations for very large (sparse (power-law)) graphs," Theoretical Computer Science, vol. 407, no. 1--3, pp. 458--473, 2008.Google Scholar
- L. Lai, L. Qin, X. Lin, and L. Chang, "Scalable subgraph enumeration in mapreduce," Proceedings of the VLDB Endowment, vol. 8, no. 10, pp. 974--985, 2015.Google ScholarDigital Library
- M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin et al., "Tensorflow: Large-scale machine learning on heterogeneous distributed systems," arXiv preprint arXiv.1603.04467, 2016.Google Scholar
- A. McCallum, K. Nigam, J. Rennie, and K. Seymore, "Automating the construction of internet portals with machine learning," Information Retrieval Journal, vol. 3, pp. 127--163, 2000.Google ScholarDigital Library
- F. M. Harper and J. A. Konstan, "The movielens datasets: History and context," ACM Transactions on Interactive Intelligent Systems (TiiS), vol. 5, no. 4, p. 19, 2016.Google ScholarDigital Library
- D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proceedings of the 3rd International Conference on Learning Representations (ICLR), 2014.Google Scholar
- A. Sankar, X. Zhang, and K. C.-C. Chang, "Motif-based convolutional neural network on graphs," arXiv preprint arXiv.1711.05697, 2017.Google Scholar
- Meta-GNN: metagraph neural network for semi-supervised learning in attributed heterogeneous information networks
Recommendations
GPT-GNN: Generative Pre-Training of Graph Neural Networks
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningGraph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs requires abundant task-specific labeled data, which is often arduously expensive to obtain. One effective way to reduce the ...
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementMeta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to ...
INS-GNN: Improving graph imbalance learning with self-supervision
AbstractGraph Neural Networks (GNNs) have achieved tremendous success in various applications, such as node classification, link prediction and graph classification. However, graph-structured data is usually imbalanced in many real-world ...
Comments