{"type":"ScholarlyArticle","title":"Learnability of Competitive Threshold Models","authors":[{"name":"Yifan Wang","slug":"yifan-wang","given":"Yifan","family":"Wang","affiliation":"Department of Computer and Information Sciences , University of Delaware , USA"},{"name":"Guangmo Tong","slug":"guangmo-tong","given":"Guangmo","family":"Tong","affiliation":"Department of Computer and Information Sciences , University of Delaware , USA"}],"abstract":"Modeling the spread of social contagions is central to various applications in social computing. In this paper, we study the learnability of the competitive threshold model from a theoretical perspective. We demonstrate how competitive threshold models can be seamlessly simulated by artificial neural networks with finite VC dimensions, which enables analytical sample complexity and generalization bounds. Based on the proposed hypothesis space, we design efficient algorithms under the empirical risk minimization scheme. The theoretical insights are finally translated into practical and explainable modeling methods, the effectiveness of which is verified through a sanity check over a few synthetic and real datasets. The experimental results promisingly show that our method enjoys a decent performance without using excessive data points, outperforming off-the-shelf methods.","doi":"10.24963/ijcai.2022/553","url":"https://ijcai.org/proceedings/2022/553","pdf":"https://ijcai.org/proceedings/2022/0553.pdf","markdown":"https://ijcai.org/proceedings/2022/553.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/553","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":553,"pages":{"first":3985,"last":3991},"keywords":["Data Mining: Theoretical Foundations of Data Mining","Data Mining: Mining Graphs","Multidisciplinary Topics and Applications: Social Sciences","Machine Learning: Learning Theory","Multidisciplinary Topics and Applications: Web  and Social Networks"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986667","length_sec":70,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984810","length_sec":357,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Adiga et al., 2019] Abhijin Adiga, Chris J Kuhlman, Mad- hav Marathe, S Ravi, and Anil Vullikanti. Pac learnabil- ity of node functions in networked dynamical systems. In Proc. of ICML, 2019.","title":"Pac learnability of node functions in networked dynamical systems","authors":"Adiga","year":"2019","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anthony et al., 1999] Martin Anthony, Peter L Bartlett, and Peter L Bartlett. Neural network learning: Theoretical foundations. Cambridge university press, 1999.","title":"Neural network learning: Theoretical foundations","authors":"Martin Anthony, Peter L Bartlett, Peter L Bartlett","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Borodin et al., 2010] Allan Borodin, Yuval Filmus, and Joel Oren. Threshold models for competitive influence in so- cial networks. In International workshop on internet and network economics. Springer, 2010.","title":"Threshold models for competitive influence in social networks","authors":"Allan Borodin, Yuval Filmus, Joel Oren","year":"2010","venue":"International workshop on internet and network economics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bozorgi et al., 2017] Arastoo Bozorgi, Saeed Samet, Johan Kwisthout, and Todd Wareham. Community-based influ- ence maximization in social networks under a competitive linear threshold model. Knowledge-Based Systems, 2017.","title":"Community-based influence maximization in social networks under a competitive linear threshold model","authors":"Arastoo Bozorgi, Saeed Samet, Johan Kwisthout, Todd Wareham","year":"2017","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Budak et al., 2011] Ceren Budak, Divyakant Agrawal, and Amr El Abbadi. Limiting the spread of misinformation in social networks. In Proc. of WWW, 2011.","title":"Limiting the spread of misinformation in social networks","authors":"Ceren Budak, Divyakant Agrawal, Amr El Abbadi","year":"2011","venue":"Proc. of WWW","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Camacho et al., 2020] David Camacho, Ángel Panizo- LLedot, Gema Bello-Orgaz, Antonio Gonzalez-Pardo, and Erik Cambria. The four dimensions of social network anal- ysis: An overview of research methods, applications, and software tools. Information Fusion, 2020.","title":"The four dimensions of social network analysis: An overview of research methods, applications, and software tools","authors":"David Camacho, Ángel Panizo-Lledot, Gema Bello-Orgaz, Antonio Gonzalez-Pardo, Erik Cambria","year":"2020","venue":"Information Fusion","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cozzo et al., 2013] Emanuele Cozzo, Raquel A Banos, San- dro Meloni, and Yamir Moreno. Contact-based social con- tagion in multiplex networks. Physical Review E, 2013.","title":"Contact-based social contagion in multiplex networks","authors":"Emanuele Cozzo, Raquel A Banos, Sandro Meloni, Yamir Moreno","year":"2013","venue":"Physical Review E","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cplex, 2009] IBM ILOG Cplex. V12. 1: User's manual for cplex. International Business Machines Corporation, 2009.","title":"IBM ILOG Cplex. V12. 1: User's manual for cplex","authors":"Cplex","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[De Domenico et al., 2013] Manlio De Domenico, Antonio Lima, Paul Mougel, and Mirco Musolesi. The anatomy of a scientific rumor. Scientific reports, 2013.","title":"The anatomy of a scientific rumor","authors":"Manlio De, Domenico, Antonio Lima, Paul Mougel, Mirco Musolesi","year":"2013","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dembo et al., 1989] Amir Dembo, Kai-Yeung Siu, and Thomas Kailath. Complexity of finite precision neural net- work classifier. In Proc. of NIPS, 1989.","title":"Complexity of finite precision neural network classifier","authors":"Amir Dembo, Kai-Yeung Siu, Thomas Kailath","year":"1989","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Du et al., 2014] Nan Du, Yingyu Liang, Maria Balcan, and Le Song. Influence function learning in information diffu- sion networks. In Proc. of ICML. PMLR, 2014.","title":"Influence function learning in information diffusion networks","authors":"Nan Du, Yingyu Liang, Maria Balcan, Le Song","year":"2014","venue":"Proc. of ICML. PMLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goldstone and Janssen, 2005] Robert L. Goldstone and Marco A. Janssen. Computational models of collective behavior. Trends in Cognitive Sciences, 9:424-430, 2005.","title":"Computational models of collective behavior","authors":"Robert L Goldstone, Marco A Janssen","year":"2005","venue":"Trends in Cognitive Sciences","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gomez-Rodriguez et al., 2016] Manuel Gomez-Rodriguez, Le Song, Nan Du, Hongyuan Zha, and Bernhard Schölkopf. Influence estimation and maximization in continuous-time diffusion networks. ACM Transactions on Information Systems (TOIS), 2016.","title":"Influence estimation and maximization in continuous-time diffusion networks","authors":"Manuel Gomez-Rodriguez, Le Song, Nan Du, Hongyuan Zha, Bernhard Schölkopf","year":"2016","venue":"ACM Transactions on Information Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2012] Xinran He, Guojie Song, Wei Chen, and Qingye Jiang. Influence blocking maximization in social networks under the competitive linear threshold model. In Proc. of ICDM. SIAM, 2012.","title":"Influence blocking maximization in social networks under the competitive linear threshold model","authors":"He","year":"2012","venue":"Proc. of ICDM. SIAM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[He et al., 2016] Xinran He, Ke Xu, David Kempe, and Yan Liu. Learning influence functions from incomplete obser- vations. In Proc. of NIPS, 2016.","title":"Learning influence functions from incomplete observations","authors":"Xinran He, Ke Xu, David Kempe, Yan Liu","year":"2016","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Holi and Hwang, 1993] Jordan L Holi and J-N Hwang. Fi- nite precision error analysis of neural network hardware implementations. IEEE Transactions on Computers, 1993.","title":"Finite precision error analysis of neural network hardware implementations","authors":"Hwang ; Holi, L Jordan, J-N Holi, Hwang","year":"1993","venue":"IEEE Transactions on Computers","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kempe et al., 2003] David Kempe, Jon Kleinberg, and Éva Tardos. Maximizing the spread of influence through a so- cial network. In Proc. of SIGKDD, 2003.","title":"Maximizing the spread of influence through a social network","authors":"David Kempe, Jon Kleinberg, Éva Tardos","year":"2003","venue":"Proc. of SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Leskovec et al., 2010] Jure Leskovec, Deepayan Chakrabarti, Jon Kleinberg, Christos Faloutsos, and Zoubin Ghahramani. Kronecker graphs: an approach to modeling networks. Journal of Machine Learning Research, 2010.","title":"Kronecker graphs: an approach to modeling networks","authors":"Jure Leskovec, Deepayan Chakrabarti, Jon Kleinberg, Christos Faloutsos, Zoubin Ghahramani","year":"2010","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Leung et al., 2019] Carson K Leung, Alfredo Cuzzocrea, Ji- axing Jason Mai, Deyu Deng, and Fan Jiang. Personalized deepinf: enhanced social influence prediction with deep learning and transfer learning. In Proc. of Big Data. IEEE, 2019.","title":"Personalized deepinf: enhanced social influence prediction with deep learning and transfer learning","authors":"Alfredo Carson K Leung, Cuzzocrea, Jason Jiaxing, Deyu Mai, Fan Deng, Jiang","year":"2019","venue":"Proc. of Big Data. IEEE","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2017] Cheng Li, Jiaqi Ma, Xiaoxiao Guo, and Qiaozhu Mei. Deepcas: An end-to-end predictor of in- formation cascades. In Proc. of WWW, 2017.","title":"Deepcas: An end-to-end predictor of information cascades","authors":"Cheng Li, Jiaqi Ma, Xiaoxiao Guo, Qiaozhu Mei","year":"2017","venue":"Proc. of WWW","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Narasimhan et al., 2015] Harikrishna Narasimhan, David C Parkes, and Yaron Singer. Learnability of influence in net- works. In Proc. of NIPS, 2015.","title":"Learnability of influence in networks","authors":"Harikrishna Narasimhan, David C Parkes, Yaron Singer","year":"2015","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pedregosa et al., 2011] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blon- del, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011.","title":"Scikit-learn: Machine learning in Python","authors":"F Pedregosa, G Varoquaux, A Gramfort, V Michel, B Thirion, O Grisel, M Blondel, P Prettenhofer, R Weiss, V Dubourg, J Vanderplas, A Passos, D Cournapeau, M Brucher, M Perrot, E Duchesnay","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Qiu et al., 2018] Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, and Jie Tang. Deepinf: Social influ- ence prediction with deep learning. In Proc. of SIGKDD, 2018.","title":"Deepinf: Social influence prediction with deep learning","authors":"Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang","year":"2018","venue":"Proc. of SIGKDD","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shalev-Shwartz and Ben-David, 2014] Shai Shalev- Shwartz and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.","title":"Understanding machine learning: From theory to algorithms","authors":"Shai Shalev, -Shwartz, Shai Ben-David","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tang et al., 2009] Jie Tang, Jimeng Sun, Chi Wang, and Zi Yang. Social influence analysis in large-scale networks. In Proc. of SIGKDD, 2009.","title":"Social influence analysis in large-scale networks","authors":"Jie Tang, Jimeng Sun, Chi Wang, Zi Yang","year":"2009","venue":"Proc. of SIGKDD","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tong et al., 2018] Guangmo Tong, Weili Wu, and Ding- Zhu Du. Coupon advertising in online social systems: Algorithms and sampling techniques. arXiv preprint arXiv:1802.06946, 2018.","title":"Coupon advertising in online social systems: Algorithms and sampling techniques","authors":"Tong","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tong, 2020] Guangmo Tong. Stratlearner: Learning a strat- egy for misinformation prevention in social networks. In Proc. of NeurIPS, 2020.","title":"Stratlearner: Learning a strategy for misinformation prevention in social networks","authors":"Guangmo Tong, Tong","year":"2020","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tzoumas et al., 2012] Vasileios Tzoumas, Christos Amana- tidis, and Evangelos Markakis. A game-theoretic analysis of a competitive diffusion process over social networks. In International Workshop on Internet and Network Eco- nomics. Springer, 2012.","title":"A game-theoretic analysis of a competitive diffusion process over social networks","authors":"Vasileios Tzoumas, Christos Amanatidis, Evangelos Markakis","year":"2012","venue":"International Workshop on Internet and Network Economics","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Weiss et al., 2018] Gail Weiss, Yoav Goldberg, and Eran Yahav. On the practical computational power of finite precision rnns for language recognition. arXiv preprint arXiv:1805.04908, 2018.","title":"On the practical computational power of finite precision rnns for language recognition","authors":"Gail Weiss, Yoav Goldberg, Eran Yahav","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}