Skip to main content

Advertisement

Springer Nature Link
Log in

Wasserstein generative adversarial networks for modeling marked events

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Marked temporal events are ubiquitous in several areas, where the events’ times and marks (types) are usually interrelated. Point processes and their non-functional variations using recurrent neural networks (RNN) model temporal events using intensity functions. However, since they usually utilize the likelihood maximization approach, they might fail. Moreover, their high simulation complexity makes them inappropriate. Since calculating the intensity function is not always necessary, generative models are utilized for modeling. Generative adversarial networks (GANs) have been successful in modeling point processes, but they still lack in modeling interdependent types and times of events. In this research, a double Wasserstein GAN (WGAN), using a conditional GAN, is proposed which generates types of events that are categorical data, dependent on their times. Experiments on synthetic and real-world data represent that WGAN methods are efficient or competitive with the compared intensity-based models. Furthermore, these methods have a faster simulation than intensity-based methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data Availability

All the datasets supporting the findings of the current study are available in github.com/hongyuanmei/neurawkes. The synthetic data generated by the self-exciting multivariate point process model (SE-MPP) in [37] were used. The Retweet dataset is the preprocessed data by Mei and Eisner in [37], which was originally prepared in [50]. The Stack Overflow and MIMIC datasets were originally prepared by Du et al. in [2], which are also available in github.com/hongyuanmei/neurawkes.

References

  1. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  2. Du N, Dai H, Trivedi R et al (2016) Recurrent marked temporal point processes: Embedding event history to vector. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, USA, KDD ’16, p 1555-1564, https://doi.org/10.1145/2939672.2939875

  3. Arjovsky M, Bottou L (2017) Towards principled methods for training generative adversarial networks. stat 1050

  4. Huszar F (2015) How (not) to train your generative model: Scheduled sampling, likelihood, adversary? CoRR abs/1511.05101. http://arxiv.org/abs/1511.05101

  5. Theis L, van den Oord A, Bethge M (2016) A note on the evaluation of generative models. CoRR abs/1511.01844

  6. Ogata Y (1981) On lewis’ simulation method for point processes. IEEE Trans Inf Theory 27:23–30

    Article  MATH  Google Scholar 

  7. Xiao S, Farajtabar M, Ye X et al (2017) Wasserstein learning of deep generative point process models. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’17, p 3250-3259

  8. Goodfellow I, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C et al (eds) Advances in Neural Information Processing Systems, vol 27. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf

  9. Goodfellow I (2016) NIPS 2016 tutorial: generative adversarial networks. arXiv e-prints arXiv:1701.00160. [cs.LG]

  10. Salimans T, Goodfellow I, Zaremba W et al (2016) Improved techniques for training gans. In: Lee D, Sugiyama M, Luxburg U, et al (eds) Advances in Neural Information Processing Systems, vol 29. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2016/file/8a3363abe792db2d8761d6403605aeb7-Paper.pdf

  11. Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70. JMLR.org, ICML’17, p 214-223

  12. Gulrajani I, Ahmed F, Arjovsky M et al (2017) Improved training of wasserstein gans. In: NIPS

  13. Kodali N, Hays J, Abernethy JD et al (2018) On convergence and stability of gans. arXiv: Artificial Intelligence

  14. Fu R, Chen J, Zeng S et al (2020) Time series simulation by conditional generative adversarial net. ERN: Time-Series Models (Single) (Topic)

  15. Yoon J, Jarrett D, van der Schaar M (2019) Time-series generative adversarial networks. In: Wallach H, Larochelle H, Beygelzimer A et al (eds) Advances in Neural Information Processing Systems, vol 32. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2019/file/c9efe5f26cd17ba6216bbe2a7d26d490-Paper.pdf

  16. Saha A, Ganguly N (2020) A gan-based framework for modeling hashtag popularity dynamics using assistive information. In: Proceedings of the 29th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, New York, NY, USA, CIKM ’20, p 1335-1344, https://doi.org/10.1145/3340531.3412025

  17. Mirza M, Osindero S (2014) Conditional generative adversarial nets. ArXiv abs/1411.1784

  18. Engelmann J, Lessmann S (2021) Conditional wasserstein gan-based oversampling of tabular data for imbalanced learning. Exp Syst Appl 174(114):582. https://doi.org/10.1016/j.eswa.2021.114582 (www.sciencedirect.com/science/article/pii/S0957417421000233)

    Article  Google Scholar 

  19. Kusner MJ, Hernández-Lobato JM (2016) Gans for sequences of discrete elements with the gumbel-softmax distribution. https://doi.org/10.48550/ARXIV.1611.04051

  20. Camino R, Hammerschmidt C, State R (2018) Generating multi-categorical samples with generative adversarial networks https://doi.org/10.48550/ARXIV.1807.01202

  21. Rocke D (2000) Genetic algorithms + data structures = evolution programs by z. michalewicz. J Am Stat Assoc 95:347–348. https://doi.org/10.2307/2669583

    Article  Google Scholar 

  22. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95 - International Conference on Neural Networks, pp 1942–1948 vol.4, https://doi.org/10.1109/ICNN.1995.488968

  23. Dorigo M, Maniezzo V, Colorni A (1999) Ant system: an autocatalytic optimizing process technical report pp. 91-016

  24. Colorni A, Dorigo M, Maniezzo V (1991) Distributed optimization by ant colonies

  25. Abualigah L, Diabat A, Mirjalili S et al (2021) The arithmetic optimization algorithm. Comput Methods Appl Mech Eng 376(113):609. https://doi.org/10.1016/j.cma.2020.113609 (www.sciencedirect.com/science/article/pii/S0045782520307945)

    Article  MathSciNet  MATH  Google Scholar 

  26. Abualigah L, Yousri D, Abd Elaziz M et al (2021) Aquila optimizer: a novel meta-heuristic optimization algorithm. Comput Ind Eng 157(107):250. https://doi.org/10.1016/j.cie.2021.107250 (www.sciencedirect.com/science/article/pii/S0360835221001546)

    Article  Google Scholar 

  27. Abualigah L, Elaziz MA, Sumari P et al (2022) Reptile search algorithm (rsa): nature-inspired meta-heuristic optimizer. Exp Syst Appl 191(116):158. https://doi.org/10.1016/j.eswa.2021.116158 (www.sciencedirect.com/science/article/pii/S0957417421014810)

    Article  Google Scholar 

  28. Agushaka JO, Ezugwu AE, Abualigah L (2022) Dwarf mongoose optimization algorithm. Comput Methods Appl Mech Eng 391(114):570. https://doi.org/10.1016/j.cma.2022.114570 (www.sciencedirect.com/science/article/pii/S0045782522000019)

    Article  MathSciNet  MATH  Google Scholar 

  29. Oyelade ON, Ezugwu AES, Mohamed TIA, et al (2022) Ebola optimization search algorithm: a new nature-inspired metaheuristic optimization algorithm. IEEE Access 10:16,150–16,177. https://doi.org/10.1109/ACCESS.2022.3147821

  30. Souza LA, Passos LA, Mendel R et al (2021) Fine-tuning generative adversarial networks using metaheuristics. In: Palm C, Deserno TM, Handels H et al (eds) Bildverarbeitung für die Medizin 2021. Springer Fachmedien Wiesbaden, Wiesbaden, pp 205–210

    Chapter  Google Scholar 

  31. Perry P, Wolfe P (2010) Point process modeling for directed interaction networks. J Royal Statistical Soc 75. https://doi.org/10.1111/rssb.12013

  32. Fox EW, Short MB, Schoenberg FP et al (2016) Modeling e-mail networks and inferring leadership using self-exciting point processes. J Am Stat Assoc 111(514):564–584. https://doi.org/10.1080/01621459.2015.1135802

    Article  MathSciNet  Google Scholar 

  33. Junuthula R, Haghdan M, Xu KS, et al (2019) The block point process model for continuous-time event-based dynamic networks. In: The World Wide Web Conference. Association for Computing Machinery, New York, NY, USA, WWW ’19, p 829-839, https://doi.org/10.1145/3308558.3313633

  34. Arastuie M, Paul S, Xu K (2020) Chip: A hawkes process model for continuous-time networks with scalable and consistent estimation. In: Larochelle H, Ranzato M, Hadsell R, et al (eds) Advances in Neural Information Processing Systems, vol 33. Curran Associates, Inc., pp 16,983–16,996, https://proceedings.neurips.cc/paper/2020/file/c5a0ac0e2f48af1a4e619e7036fe5977-Paper.pdf

  35. Wang Y, Liu S, Shen H, et al (2017) Marked temporal dynamics modeling based on recurrent neural network. pp 786–798, https://doi.org/10.1007/978-3-319-57454-7_61

  36. Xiao S, Yan J, Farajtabar M, et al (2017) Joint modeling of event sequence and time series with attentional twin recurrent neural networks. arXiv: 1703.08524

  37. Mei H, Eisner J (2017) The neural hawkes process: a neurally self-modulating multivariate point process. In: Guyon I, von Luxburg U, Bengio S, et al (eds) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9, 2017, Long Beach, CA, USA, pp 6754–6764, https://proceedings.neurips.cc/paper/2017/hash/6463c88460bd63bbe256e495c63aa40b-Abstract.html

  38. Cai H, Nguyen T, Li Y et al (2020) Modeling marked temporal point process using multi-relation structure rnn. Cognitive Computation 12. https://doi.org/10.1007/s12559-019-09690-8

  39. Abu-Srhan A, Abushariah MA, Al-Kadi OS (2022) The effect of loss function on conditional generative adversarial networks. J King Saud Univ- Comput Inf Sci. https://doi.org/10.1016/j.jksuci.2022.02.018

    Article  Google Scholar 

  40. Chapfuwa P, Tao C, Li C et al (2018) Adversarial time-to-event modeling. Proceedings of machine learning research 80

  41. Xu L, Skoularidou M, Cuesta-Infante A et al (2019) Modeling tabular data using conditional GAN. Curran Associates Inc., Red Hook, NY, USA

    Google Scholar 

  42. Zhao Z, Kunar A, Van der Scheer H et al (2021) Ctab-gan: effective table data synthesizing. https://doi.org/10.48550/ARXIV.2102.08369

  43. Hawkes AG (1971) Spectra of some self-exciting and mutually exciting point processes. Biometrika 58(1):83–90 (http://www.jstor.org/stable/2334319)

    Article  MathSciNet  MATH  Google Scholar 

  44. Hawkes AG (1971) Spectra of some self-exciting and mutually exciting point processes. Biometrika 58(1):83–90 (http://www.jstor.org/stable/2334319)

    Article  MathSciNet  MATH  Google Scholar 

  45. Gulddahl Rasmussen J (2018) Lecture notes: temporal point processes and the conditional intensity function. arXiv e-prints arXiv:1806.00221. [stat.ME]

  46. Lewis E, Mohler G (2011) A nonparametric em algorithm for multiscale hawkes processes. J Nonparamet Statistics

  47. Villani C (2008) Optimal Transport: Old and New. Grundlehren der mathematischen Wissenschaften, Springer Berlin Heidelberg, https://books.google.com/books?id=hV8o5R7_5tkC

  48. Gumbel EJ (1954) Statistical theory of extreme values and some practical applications; a series of lectures. Appl Math Series ; 33, U.S. Govt. Print. Office, Washington

  49. Jang E, Gu SS, Poole B (2017) Categorical reparameterization with gumbel-softmax. ArXiv abs/1611.01144

  50. Zhao Q, Erdogdu MA, He HY et al (2015) Seismic: a self-exciting point process model for predicting tweet popularity. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, USA, KDD ’15, p 1513-1522, https://doi.org/10.1145/2783258.2783401

Download references

Funding

No funding was received to assist with the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran

    S. Haleh S. Dizaji, Saeid Pashazadeh & Javad Musevi Niya

Authors
  1. S. Haleh S. Dizaji
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Saeid Pashazadeh
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Javad Musevi Niya
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Saeid Pashazadeh.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dizaji, S.H.S., Pashazadeh, S. & Niya, J.M. Wasserstein generative adversarial networks for modeling marked events. J Supercomput 79, 2961–2983 (2023). https://doi.org/10.1007/s11227-022-04781-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04781-0

Keywords