Abstract
Attributed network representation learning is to embed graphs in low dimensional vector space such that the embedded vectors follow the differences and similarities of the source graphs. To capture structural features and node attributes of attributed network, we propose a novel graph auto-encoder method which is stacked encoder-decoder layers based on graph attention with robust negative sampling. Here, minimize the negative log-likelihood, triplet distance, and weighted neighborhood attributes are proposed as the loss function. To alleviate the over-fitting on reconstruct graph structural features or node attributes, a trade off algorithm between reconstruction loss of node attributes and reconstruction loss of structural features is proposed. Furthermore, to alleviate the impact of random sampling, we propose additional constraints on negative sampling based on node degree. Experimental results on several benchmark datasets for transductive and inductive learning tasks show that the proposed model is competitive against well-known methods in node classification and link prediction.
Similar content being viewed by others
Notes
Our implementation of the GARNS may be found at https://github.com/fanhl/GARNS
References
Mercado P, Bosch J, Stoll M (2019) Node classification for signed social networks using diffuse interface methods. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 524-540). Springer, Cham
Tuan TM, Chuan PM, Ali M, Ngan TT, Mittal M (2019) Fuzzy and neutrosophic modeling for link prediction in social networks. Evolving Systems 10(4):629–634
Zeng X, Wang W, Chen C, Yen GG (2019) A consensus community-based particle swarm optimization for dynamic community detection. IEEE transactions on cybernetics
Dai Q, Li Q, Zhang L, Wang D (2019) Ranking Network Embedding via Adversarial Learning. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 27-39). Springer, Cham
Li C, Guan D, Yuan W (2019) Network Embedding via Link Strength Adjusted Random Walk. In: Pacific Rim Knowledge Acquisition Workshop (pp. 163-172). Springer, Cham
Jung J, Jin W, Kang U (2020) Random walk-based ranking in signed social networks: Model and algorithms. Knowl Inf Syst 62(2):571–610
Ying R, He R, Chen K, Eksombatchai P, Hamilton WL, Kang U, Leskovec J (2018) Graph convolutional neural networks for web-scale recommender systems, pp 974–983
Guan N, Song D, Liao L (2019) Knowledge graph embedding with concepts. Knowledge-Based Systems 164:38–44
Sheikh N, Kefato Z, Montresor A (2019) Gat2vec: representation learning for attributed graphs. Computing 101(3):187–209
Wang R, Wang M, Liu J, Cochez M, Decker S (2019) Structured query construction via knowledge graph embedding. Knowl Inf Syst 62(5):1819–1846
Chen H, Perozzi B, Hu Y, Skiena S (2018) Harp: Hierarchical representation learning for networks. In: Thirty-Second AAAI Conference on Artificial Intelligence
Zamora-Resendiz R, Crivelli S (2019) Structural Learning of Proteins Using Graph Convolutional Neural Networks. bioRxiv, 610444
Rossi RA, Zhou R, Ahmed N (2018) Deep inductive graph representation learning. IEEE Transactions on Knowledge and Data Engineering
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907
Monti F, Boscaini D, Masci J, Rodola E, Svoboda J, Bronstein MM (2017) Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5115–5124
Zhou H, Young T, Huang M, Zhao H, Xu J, Zhu X (2018) Commonsense Knowledge Aware Conversation Generation with Graph Attention. In: IJCAI, pp 4623–4629
Lou Y, Qian T, Li F, Ji D (2020) A Graph Attention Model for Dictionary-Guided Named Entity Recognition. IEEE Access 8:71584–71592
Song W, Xiao Z, Wang Y, Charlin L, Zhang M, Tang J (2019) Session-based social recommendation via dynamic graph attention networks. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, pp 555–563
Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv:1710.10903
Huang Z, Li X, Ye Y, Li F, Yao Y (2018) Tlvane: A two-level variation model for attributed network embedding. Neural Computing & Applications(6)
Shen C, Zhao X, Fan X, Lian X, Zhang F, Kreidieh AR, Liu Z (2019) Multi-receptive field graph convolutional neural networks for pedestrian detection. IET Intelligent Transport Systems 13 (9):1319–1328
Hong R, He Y, Wu L, Ge Y, Wu X (2019) Deep attributed network embedding by preserving structure and attribute information. IEEE Transactions on Systems, Man, and Cybernetics: Systems
Pan S, Hu R, Long G, Jiang J, Yao L, Zhang C (2018) Adversarially regularized graph autoencoder for graph embedding. arXiv:1802.04407
Ren Y, Liu B, Huang C, Dai P, Bo L, Zhang J (2019) Heterogeneous Deep Graph Infomax. arXiv:1911.08538
Wang C, Pan S, Long G, Zhu X, Jiang J (2017) Mgae: Marginalized graph autoencoder for graph clustering. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp 889–898
Salehi A, Davulcu H (2019) Graph Attention Auto-Encoders. arXiv:1905.10715
Guo W, Cai J, Wang S (2020) Unsupervised discriminative feature representation via adversarial auto-encoder. Appl Intell 50(4):1155–1171
Bojchevski A, Günnemann S (2017) Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. arXiv:1707.03815
Zhang L, Liu Z, Wang L, Pu J (2019) Adaptive Graph Regularization Discriminant Nonnegative Matrix Factorization for Data Representation. IEEE Access 7:112756–112766
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 701–710
Grover A, Leskovec J (2016) Node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp 855–864
Lin CH, Wang SH, Lin CJ (2019) Using convolutional neural networks for character verification on integrated circuit components of printed circuit boards. Applied Intelligence 49(11):4022– 4032
Yang Z, Cohen WW, Salakhutdinov R (2016) Revisiting semi-supervised learning with graph embeddings. arXiv:1603.08861
Zhang D, Yin J, Zhu X, Zhang C (2019) Attributed network embedding via subspace discovery. Data Mining and Knowledge Discovery 33(6):1953–1980
Galland A, Lelarge M (2019) Invariant embedding for graph classification. In: ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Representations
Bahonar H, Mirzaei A, Wilson R (2019) Graph Embedding Using Frequency Filtering. IEEE transactions on pattern analysis and machine intelligence
Hasanzadeh A, Hajiramezanali E, Narayanan K, Duffield N, Zhou M, Qian X (2019) Semi-implicit graph variational auto-encoders. In: Advances in Neural Information Processing Systems, pp 10711–10722
Zhang Z, Yang H, Bu J, Zhou S, Yu P, Zhang J, Wang C (2018) ANRL: Attributed Network Representation Learning via Deep Neural Networks. . In: IJCAI, 18, pp 3155–3161
Wang G, Ying R, Huang J, Leskovec J (2019) Improving Graph Attention Networks with Large Margin-based Constraints. arXiv:1910.11945
Gong L, Cheng Q (2019) Exploiting edge features for graph neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 9211–9219
Cai H, Zheng VW, Chang KCC (2018) A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Transactions on Knowledge and Data Engineering 30(9):1616–1637
Shankar Shanthamallu U, Thiagarajan JJ, Song H, Spanias A (2018) GrAMME:, Semi-Supervised Learning using Multi-layered Graph Attention Models. arXiv:1810.01405
Horrocks T, Holden EJ, Wedge D, Wijns C, Fiorentini M (2019) Geochemical characterisation of rock hydration processes using t-SNE. Computers & geosciences 124:46–57
Wang P, Zhao J, Zhang X, Tao J, Guan X (2019) SNOD: a fast sampling method of exploring node orbit degrees for large graphs. Knowledge and Information Systems 61(1):301–326
Acknowledgements
This work is supported by the Natural Science Foundation of Chongqing (No.cstc2019jscx-msxm0616), the Fundamental Research Funds for the Central Universities (No.2019CDCGTX302, No.2018CDPTCG000141) and the Major Natural Science Funds of Chongqing Education Commission(No.KJZD-M201901401)
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fan, H., Zhong, Y., Zeng, G. et al. Attributed network representation learning via improved graph attention with robust negative sampling. Appl Intell 51, 416–426 (2021). https://doi.org/10.1007/s10489-020-01825-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01825-x