Abstract
Network representation learning (NRL) is effective in generating node embeddings. To predict heterogeneous links between different types of nodes, NRL is not robustly investigated yet. Though existing studies on random walk-based heterogeneous NRL are available, it suffers from three drawbacks: need to specify “templates” (e.g., metapaths), require separate embedding learning in predicting heterogeneous links, and opt to generate low-quality embeddings when networks are incomplete or sparse. This work proposes a novel template-free NRL method, metawalk2vec, to tackle these issues for heterogeneous link prediction. The idea is allowing the random walker to visit diverse types of nodes, instead of following the pre-defined templates. While template-based methods use common context patterns for NRL, nodes depicted by uncommon context types can make their embeddings better distinguish from each other. We conduct the experiments of social (user-user) and adoption (user-item) link predictions on Twitter and Douban datasets. The results exhibit our metawalk2vec can achieve similar and even better performance than template-based models. We also show our model is more robust to the network incompleteness.
Similar content being viewed by others
References
Backstrom L, Leskovec J (2011) Supervised random walks: predicting and recommending links in social networks. In: Proceedings of the fourth ACM international conference on web search and data mining, WSDM ’11, pp 635–644
Beigi G, Liu H (2018) Privacy in social media: identification, mitigation and applications. CoRR arXiv:808.02191
Chakrabarti Deepayan, Faloutsos Christos (2006) Graph mining: laws, generators, and algorithms. ACM Comput Surv 38(1):2-es
Dareddy MR, Das M, Yang H(2019) motif2vec: motif aware node representation learning for heterogeneous networks
Dong Y, Chawla NV, Swami A (2017) Metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’17, pp 135–144
Fu X, Zhang J, Meng Z, King I (2020) Magnn: metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of the web conference 2020, WWW ’20, pp 2331–2341
Gao H, Huang H (2018) Deep attributed network embedding. In: Proceedings of the 27th international joint conference on artificial intelligence, IJCAI ’18, pp 3364–3370
Gao Z, Fu G, Ouyang C, Tsutsui S, Liu X, Yang J, Gessner C, Foote B, Wild D, Ding Yi YuQ (2019) edge2vec: representation learning using edge semantics for biomedical knowledge discovery. BMC Bioinform 20:1–5
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, KDD ’16, pp 855–864
Hakak Saqib, Alazab Mamoun, Khan Suleman, Gadekallu Thippa Reddy, Maddikunta Praveen Kumar Reddy, Khan Wazir Zada (2021) An ensemble machine learning approach through effective feature extraction to classify fake news. Future Gener Comput Syst 117:47–58
Hsieh Hsun-Ping, Li Cheng-Te (2019) Inferring online social ties from offline geographical activities. ACM Trans Intell Syst Technol 10(2):17:1–17:21
Hsieh H-P, Yan R, Li C-T (2015) Where you go reveals who you know: analyzing social ties from millions of footprints. In: Proceedings of the 24th ACM international on conference on information and knowledge management, CIKM ’15, pp 1839–1842
Hu B, Shi C, Zhao WX, Yu PS (2018) Leveraging meta-path based context for top-n recommendation with a neural co-attention model. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’18, pp 1531–1540
Hu Z, Dong Y, Wang K, Sun Y (2020) Heterogeneous graph transformer. In: Proceedings of the web conference 2020, WWW ’20, pp 2704–2710
Hussein R, Yang D, Cudré-Mauroux P (2018) Are meta-paths necessary? Revisiting heterogeneous graph embeddings. In: Proceedings of the 27th ACM international conference on information and knowledge management, CIKM ’18, pp 437–446
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th international conference on learning representations, ICLR ’17
Liben-Nowell D, Kleinberg J (2003) The link prediction problem for social networks. In: Proceedings of the twelfth international conference on information and knowledge management, CIKM ’03, pp 556–559
Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. CoRR
Mislove A, Viswanath B, Gummadi KP, Druschel P (2010) You are who you know: inferring user profiles in online social networks. In: Proceedings of the third ACM international conference on web search and data mining, WSDM ’10, pp 251–260
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, KDD ’14, pp 701–710
Tang J, Qu M, Mei Q (2015) Pte: predictive text embedding through large-scale heterogeneous text networks. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’15, pp 1165–1174
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, WWW ’15, pp 1067–1077
Wang X, Zhang Y, Shi C (2019) Hyperbolic heterogeneous information network embedding. In: Proceedings of the thirty-third AAAI conference on artificial intelligence, AAAI ’19, pp 5337–5344
Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS (2021) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24
Zhang D, Yin J, Zhu X, Zhang C (2018) Metagraph2vec: complex semantic path augmented heterogeneous network embedding. In: Pacific-Asia conference on knowledge discovery and data mining, PAKDD ’18, pp 196–208
Zhu Z, Fan X, Chu X, Bi J (2020) Hgcn: a heterogeneous graph convolutional network-based deep learning model toward collective classification. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, KDD ’20, pp 1161–1171
Acknowledgements
This work is supported by Ministry of Science and Technology (MOST) of Taiwan under grants 109-2636-E-006-017 (MOST Young Scholar Fellowship), 110-2221-E-006-001, and 110-2221-E-006 -136-MY3.
Funding
This work is supported by Ministry of Science and Technology (MOST) of Taiwan under Grants 109-2636-E-006-017 (MOST Young Scholar Fellowship), 110-2221-E-006-001, and 110-2221-E-006 -136-MY3.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Author Cheng-Te Li declares that he has no conflict of interest. Author Wei-Chu Wang declares that she has no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the 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
Li, CT., Wang, WC. Learning template-free network embeddings for heterogeneous link prediction. Soft Comput 25, 13425–13435 (2021). https://doi.org/10.1007/s00500-021-06090-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-021-06090-9