Research

Research Area

Artificial intelligence and machine learning: causal inference, graphical models, adversarial attacks & robustness.

Publications

• Y. Jung, I. Díaz, J. Tian, E. Bareinboim. Estimating Causal Effects Identifiable from a Combination of Observations and Experiments, In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS), 2023.                                                                                                                                                                                          
• Lale Madahali, Jin Tian. Bots: Genuine or Malicious, in Proceedings of 2023 IEEE 14th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2023.
• Lale Madahali, Jin Tian. I'm Not a Human: A Comparison of Bot and Human Self-Presentation, in Proceedings of 2023 IEEE 14th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2023.    
• Olukorede Fakorede, Ashutosh Nirala, Modeste Atsague, Jin Tian, Vulnerability-Aware Instance Reweighting For Adversarial Training, Transactions on Machine Learning Research, 2023.                                                                                                                                                                                    
• Modeste Atsague, Ashutosh Nirala, Olukorede Fakorede, Jin Tian, A Penalized Modified Huber Regularization to Improve Adversarial Robustness, in Proceedings of IEEE International Conference on Image Processing (ICIP), 2023.                                                                                                                                                                                                 
• Yuta Kawakami, Manabu Kuroki, Jin Tian. Instrumental Variable Estimation of Average Partial Causal Effects. In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023.                                                                                                                                                                                                                                                                                        
• Y. Jung, J. Tian, and E. Bareinboim, Estimating Joint Treatment Effects by Combining Multiple Experiments. In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023.                                                                                                                                                                   
• Olukorede Fakorede, Ashutosh Nirala, Modeste Atsague, Jin Tian, Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizations, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP), 2023.                                                    
• T. V. Anand, A. H. Ribeiro, J. Tian, and E. Bareinboim. Causal Effect Identification in Cluster DAGs. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.                                                                                                                                                                                                
• H. Jeong, J. Tian, E. Bareinboim. Finding and Listing Front-door Adjustment Sets, In Proceedings of the 36th Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.                                                                                  
• Yaojie Hu and Jin Tian, Neuron Dependency Graphs: A Causal Abstraction of Neural Networks, In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
• J. Zhang, J. Tian, E. Bareinboim. Partial Counterfactual Identification from Observational and Experimental Data. In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
• Y. Jung, S. Kasiviswanathan, J. Tian, D. Janzing, P. Bloebaum, E. Bareinboim. On Measuring Causal Contributions via do-Interventions, In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
• Qi Xiao, Hebi Li, Jin Tian, and Zhengdao Wang, Group-wise Feature Selection for Supervised Learning, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP), 2022.
• Youbiao He, Hebi Li, Forrest Bao, and Jin Tian, Circuit Routing Using Monte Carlo Tree Search and Deep Reinforcement Learning, in Proceedings of the International Symposium on VLSI Design, Automation and Test (VLSI-DAT), 2022.
• Y. Jung, J. Tian, and E. Bareinboim, Double Machine Learning Density Estimation for Local Treatment Effects with Instruments. In Proceedings of the 35th Annual Conference on Neural Information Processing Systems (NeurIPS), 2021.
• Modeste Atsague, Olukorede Fakorede, and Jin Tian, A Mutual Information Regularization for Adversarial Training, in Proceedings of the Asian Conference on Machine Learning (ACML), 2021.                                                                                                                                                                                                                                           
• Eliska Kloberdanz, Jin Tian, and Wei Le, An Improved (Adversarial) Reprogramming Technique for Neural Networks, in 30th International Conference on Artificial Neural Networks (ICANN), 2021.                                                                                                                                                                                            
• Y. Jung, J. Tian, and E. Bareinboim, Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning. In Proceedings of the 38th International Conference on Machine Learning (ICML), 2021.                                                                                                                 
• Hebi Li, Youbiao He, Qi Xiao, Jin Tian, and Forrest Sheng Bao, BHDL: A Lucid, Expressive, and Embedded Programming Language and System for PCB Designs, ACM/IEEE 58th Design Automation Conference (DAC), 2021.                                                                                                                              
• Minghong Fang, Minghao Sun, Qi Li, Neil Zhenqiang Gong, Jin Tian, and Jia Liu, Data Poisoning Attacks and Defenses to Crowdsourcing Systems. In Proc. of the Web Conference (WWW), 2021.                                                                                                                                                       
• Y. Jung, J. Tian, and E. Bareinboim, Estimating Identifiable Causal Effects through Double Machine Learning. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021.                                                                                                                                                                       
• Hebi Li, Qi Xiao, and Jin Tian, Supervised Whole DAG Causal Discovery. arXiv:2006.04697, 2020.
• Y. Jung, J. Tian, and E. Bareinboim, Learning Causal Effects via Weighted Empirical Risk Minimization. In Proceedings of the 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020. 
• Y. Jung, J. Tian, and E. Bareinboim, Estimating Causal Effects Using Weighting-Based Estimators. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020.
• M. Saadati and J. Tian, Adjustment Criteria for Recovering Causal Effects from Missing Data, in Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2019. (arXiv:1907.01654)
• K Koo, M Govindarasu, J Tian, Event prediction algorithm using neural networks for the power management system of electric vehicles, Applied Soft Computing, Vol. 84, 2019.
• J. Correa, J. Tian, and E. Bareinboim, Adjustment Criteria for Generalizing Experimental Findings, in Proceedings of the 36th International Conference on Machine Learning (ICML), 2019.
• J. Correa, J. Tian, and E. Bareinboim, Identification of Causal Effects in the Presence of Selection Bias, in Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 2019.
• J. Correa, J. Tian, and E. Bareinboim, Generalized Adjustment Under Confounding and Selection Biases, in Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), February 2-7, 2018. New Orleans, Louisiana, USA. (AAAI-18 Outstanding Paper Honorable Mention)
• Jin Tian, Recovering Probability Distributions from Missing Data, in Proceedings of the 9th Asian Conference on Machine Learning (ACML), 2017. Seoul, Korea.
• Yanpeng Zhao, Yetian Chen, Kewei Tu, and Jin Tian. Learning Bayesian Network Structures Under Incremental Construction Curricula. Neurocomputing, Volume 258, Pages 30-40, 2017.
• Yetian Chen, Jin Tian, Olga Nikolova, Srinivas Aluru. A Parallel Algorithm for Exact Bayesian Structure Discovery in Bayesian Networks. arXiv:1408.1664. (ParaREBEL software)
• Ru He, Jin Tian, and Huaiqing Wu, Structure Learning in Bayesian Networks of a Moderate Size by Efficient Sampling, the Journal of Machine Learning Research (JMLR) 17(101):1-54, 2016. (BNLearner Software)
• Yetian Chen, Jose P. Gonzalez-Brenes, and Jin Tian. Joint Discovery of Skill Prerequisite Graphs and Student Models, in Proceedings of the 9th International Conference on Educational Data Mining (EDM), June 29 - July 2, 2016. Raleigh, North Carolina, USA. (Full Paper)
• Yanpeng Zhao, Yetian Chen, Kewei Tu, and Jin Tian. Curriculum Learning of Bayesian Network Structures. The 7th Asian Conference on Machine Learning (ACML), Hong Kong, 2015. (supplementary material)  (Software)
• J. Tian. Missing at Random in Graphical Models, in Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS) 2015, San Diego, CA, USA. JMLR: W&CP volume 38.
• Y. Chen, L. Meng, and J. Tian. Exact Bayesian Learning of Ancestor relations in Bayesian Networks, in Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS) 2015, San Diego, CA, USA. JMLR: W&CP volume 38. (supplemental material) (PosteriorAncestor Software)
• E. Bareinboim and J. Tian, Recovering Causal Effects from Selection Bias, in Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), January 25-30, 2015. Austin, Texas, USA.
• Y. Chen and J. Tian, Finding the k-best Equivalence Classes of Bayesian Network Structures for Model Averaging, in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), July 27-31, 2014. Quebec City, Canada. (supplemental materials) (KBestEC software)
• B. Chen, J. Tian, and J. Pearl, Testable Implications of Linear Structural Equations Models, in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), July 27-31, 2014. Quebec City, Canada.
• E. Bareinboim, J. Tian, and J. Pearl, Recovering from Selection Bias in Causal and Statistical Inference, in Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), July 27-31, 2014. Quebec City, Canada. (supplementary material) (AAAI-14 Outstanding Paper Award). A notable paper in computing in the ACM Computing Reviews' 19th Annual Best of Computing.  
• K. Mohan, J. Pearl, and J. Tian, Graphical Models for Inference with Missing Data, in C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 26 (NIPS 2013), 1277--1285, 2013.
• R. He, J. Wang, J. Tian, C. Chu, B. Mauney, and I. Perisic, Session Analysis of People Search within a Professional Social Network, Journal of the American Society for Information Science and Technology, 64: 929-950, 2013. doi: 10.1002/asi.22814.
• J. Tian, R. He, and L. Ram, Bayesian Model Averaging Using the k-best Bayesian Network Structures, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2010. Catalina Island, California. (Download KBest software)
• J. Tian, and I. Shpitser, On Identifying Causal Effects, In R. Dechter, H. Geffner, and J. Halpern (Eds.), Heuristics, Probability and Causality: A Tribute to Judea Pearl, College Publications, 2010.
• J. Tian and R. He, Computing Posterior Probabilities of Structural Features in Bayesian Networks, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), June 18-21, 2009. (Download POSTER software)
• J. Tian, Parameter Identification in a Class of Linear Structural Equation Models, in Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), July 11-17, 2009. Pasadena, California. pp. 1970-1975.
• C. Kang, J. Tian, Markov Properties for Linear Causal Models with Correlated Errors, the Journal of Machine Learning Research (JMLR), Vol. 10, 41-70, 2009.
• CIBN software for causal inference in causal Bayesian networks with hidden variables.
• J. Tian, Identifying Dynamic Sequential Plans, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI),  2008.
• Z. Cai, M. Kuroki, J. Pearl, and J Tian, Bounds on Direct Effects in the Presence of Confounded Intermediate Variables, Biometrics, Vol. 64, 695-701, 2008. (Supplementary_materials)
• J. Tian, On the Identification of a Class of Linear Models. Proceedings of the National Conference on Artificial Intelligence (AAAI), July 22-26, 2007. Vancouver, Canada. AAAI Press, pp. 1284-1289.
• J. Tian, A Criterion for Parameter Identification in Structural Equation Models, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), July 19-22, 2007. Vancouver, Canada. AUAI Press, pp. 392-399.
• C. Kang, J. Tian, Polynomial Constraints in Causal Bayesian Networks, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), July 19-22, 2007. Vancouver, Canada. AUAI Press, pp. 200-208.
• J. Tian, C. Kang, and J. Pearl, A Characterization of Interventional Distributions in Semi-Markovian Causal Models. Proceedings of the National Conference on Artificial Intelligence (AAAI), July 16-20, 2006. Boston, Massachusetts. AAAI Press, pp. 1239-1244.
• C. Kang and J. Tian, Inequality Constraints in Causal Models with Hidden Variables, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), July 13-16, 2006. Cambridge, Massachusetts. AUAI Press, pp. 233-240.
• C. Kang and J. Tian, A Hybrid Generative/Discriminative Bayesian Classifier. Proceedings of the 19th International Florida Artificial Intelligence Research Society Conference (FLAIRS), May 11-13, 2006. Melbourne Beach, Florida. AAAI Press, pp. 562-567.
• J. Tian, Identifying Direct Causal Effects in Linear Models, in Proceedings  of the National Conference on Artificial Intelligence (AAAI), 2005.
• C. Kang and J. Tian,  Local Markov Property for Models Satisfying Composition Axiom, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2005.
• J. Tian,  Generating Markov Equivalent Maximal Ancestral Graphs by Single Edge Replacement, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2005.
• J. Tian, Identifying linear causal effects, in Proceedings of the National Conference on Artificial Intelligence (AAAI), 2004.
• J. Tian,  Identifying Conditional Causal Effects, in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2004.
• J. Tian and J. Pearl, On the identification of causal effects, UCLA Cognitive Systems Laboratory, Technical Report (R-290-L), 2003.
• J. Tian and J. Pearl, On the Testable Implications of Causal Models with Hidden Variables,  in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2002.
• J. Tian and J. Pearl, A general identification condition for causal effects, in Proceedings  of the National Conference on Artificial Intelligence (AAAI), 2002.
• J. Tian and J. Pearl, A new characterization of the experimental implications of causal Bayesian networks in Proceedings  of the National Conference on Artificial Intelligence (AAAI), 2002.
• J. Tian and J. Pearl, ``Causal Discovery from Changes: a Bayesian Approach'', UCLA Cognitive Systems Laboratory, Technical Report (R-285), February 2001.
• J. Tian and J. Pearl, ``Causal Discovery from Changes'', in Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2001.
• J. Tian and J. Pearl, ``Probabilities of causation: Bounds and identification'', in Annals of Mathematics and Artificial Intelligence 28 (2000) 287-313.
• J. Tian, ``A Branch-and-Bound Algorithm for MDL Learning Bayesian Networks'', in Craig Boutilier and Moises Goldszmidt (Eds.), Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI-2000), San Francisco, CA: Morgan Kaufmann, 580--588, 2000.
• J. Tian and J. Pearl, ``Probabilities of causation: Bounds and identification'', in Craig Boutilier and Moises Goldszmidt (Eds.), Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI-2000), San Francisco, CA: Morgan Kaufmann, 589--598, 2000.
• J. Tian, A. Paz, and J. Pearl, ``Finding minimal d-separating sets'', UCLA Cognitive Systems Laboratory, Technical Report (R-254), 1998.