My research largely focuses on the role of technology and Artificial Intelligence in social systems. I focus on theoretical and applied aspects of Data Science and Machine Learning to investigate social and business processes, the structure of evolving complex systems, such as social and information networks, and on computational social science.
1. Zheng Wang, Bruno Abrahao, Ece Kamar, Supervised Discovery of Unknown Unknowns through Test Sample Mining, The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) 2020.
2. Bruno Abrahao, Paolo Parigi, The emergence of networks from the ground up: computational solutions to new big data problems, Moody, James (Ed.): The Oxford Handbook of Social Networks , Oxford Press, 2020.
3. Koustuv Saha, Benjamin Sugar, John Torous, Bruno Abrahao, Emre Kıcıman, Munmun De Choudhury, A Social Media Study on the Effects of Psychiatric Medication Use, International Association for the Advancement of Artificial Intelligence Conference on Web and Social Media 2019 (Outstanding Study Design Paper Award).
4. Will Qiu, Paolo Parigi, Bruno Abrahao, More Stars or More Reviews? Differential Effects of Reputation on Trust in the Sharing Economy, Proceedings of the ACM CHI Conference on Human Factors in Computing Systems, pp. 1-11, 2018.
5. Bruno Abrahao, Paolo Parigi, Alok Gupta, Karen S. Cook, Reputation offsets trust judgments based on social biases among Airbnb users, Proceedings of the National Academy of Sciences, 114 (37), pp. 9848–9853, 2017.
My current research interests are in the area of computer vision and deep learning, including semantic segmentation and object detection.
1. Liang Han, Zhaozheng Yin, Zhurong Xia, Li Guo, Rong Jin, Price Suggestion for Online Second-hand Items with Texts and Images, ACM Multimedia Conference (ACM MM), 2020.
2. Subir Ghosh, Li Guo, Luyao Peng, Variance component estimators OPE, NOPE and AOPE in linear mixed effects models, Australian & New Zealand Journal of Statistics 60 (4), 481-505, 2018.
3. Daniel R. Jeske, Terrance P. Callanan, Li Guo, Identification of Key Drivers of Net Promoter Score Using a Statistical Classification Model, in book Efficient Decision Support Systems: Practice and Challenges From Current to Future, 2011.
4. Li Guo, Daniel R. Jeske, Reviews on “A Cost Savings Analysis of Skin Closure Devices", American Journal of Cosmetic Surgery, Vol. 28, Issue 1, pp. 47-50, 2011.
5. Li Guo, Jeske, Daniel R. Jeske, Reviews on “Intense Pulsed Light Plus Oral Isotretinoin in Facial Rejuvenation”, American Journal of Cosmetic Surgery, Vol. 28, Issue1, pp.50-pp53, 2011.
I am broadly interested in solving problems involving fine-grained human behavior. This research lies in the intersection of Machine Learning and Business.
1. EJ de Fortuny, D Martens, and F Provost, Wallenius bayes. Machine Learning, 107(6), pp.1013-1037, 2018.
2. D Martens, J Clark, F Provost, EJ de Fortuny, Mining Massive Fine-Grained Behavior Data to Improve Predictive Analytics, MIS quarterly, 40(4), 2016.
3. EJ de Fortuny, D Martens, Active learning-based pedagogical rule extraction, IEEE transactions on neural networks and learning systems, 26(11), pp.2664-2677, 2015.
4. EJ de Fortuny, T De Smedt, D Martens, W Daelemans, Evaluating and understanding text-based stock price prediction models, Information Processing & Management, 50(2), 426-441, 2014.
5. EJ de Fortuny, D Martens, F Provost, Predictive modeling with big data: is bigger really better?. Big Data, 1(4), pp.215-226, 2013.
I am interested in the irrationality of artificial intelligence. This research is at the intersection of decision theory, behavioral economics economics, computer science (machine learning), and statistical modeling.
1. Joshua Batson, Grace Haaf, Yonatan Kahn, and Daniel A. Roberts, Topological Obstructions to Autoencoding, arXiv preprint arXiv:2102.08380, 2021.
2. Grace Haaf, W. Ross Morrow, Inês ML Azevedo, Elea McDonnell Feit, and Jeremy J. Michalek, Forecasting light-duty vehicle demand using alternative-specific constants for endogeneity correction versus calibration, Transportation Research Part B: Methodological 84: 182-210, 2016.
3. Grace Heckman, Jeremy J. Michalek, W. Ross Morrow, and Yimin Liu, Sensitivity of vehicle market share predictions to alternative discrete choice model specifications, ASME 2013 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, American Society of Mechanical Engineers Digital Collection, 2013.
4. Camilo B. Resende, C. Grace Heckmann, and Jeremy J. Michalek, Robust design for profit maximization with aversion to downside risk from parametric uncertainty in consumer choice models, Journal of mechanical design 134, no. 10, 2012.
My research interests focus broadly on mathematics of data science including compressive sensing, low-rank matrix recovery, optimization, computational mathematics, random matrix, and machine learning. My recent projects include group synchronization and community detection in directed networks.
1. S. Ling*, Solving orthogonal group synchronization via convex optimization and low-rank optimization: tightness and landscape analysis, arXiv:2006.00902, 2020, Submitted.
2. S. Ling, T. Strohmer, Certifying global optimality of graph cuts via semidefinite relaxation: a performance guarantee for spectral clustering, Foundation of Computational Mathematics, 20(3):368-421, 2020.
3. X. Li, Y. Li, S. Ling, T. Strohmer, K. Wei, When do birds of a feather flock together? k-means, proximity, and conic programming, Mathematical Programming, Series A, 179(1):295-341, 2020.
4. S. Ling, R. Xu, A. S. Bandeira, On the landscape of synchronization networks: a perspective from nonconvex optimization, SIAM Journal on Optimization, 29(3):1879-1907, 2019.
5. X. Li, S. Ling, T. Strohmer, K. Wei, Rapid, robust, and reliable blind deconvolution via nonconvex optimization, Applied and Computational Harmonic Analysis, 47(3):893-934, 2019.
My research interests cover the algorithms and mathematics of deep learning. Currently, my group is mostly focused on deep reinforcement learning, a branch of machine learning that combines reinforcement learning with neural networks to solve sequential decision problems at scale.
1. Xinyue Chen, Che Wang, Zijian Zhou, Keith Ross, Randomized Ensembled Double Q-Learning: Learning Fast without a Model, to be appear in International Conference on Learning Representations (ICLR) 2021.
2. Yiming Zhang, Quon Voung, Keith Ross, First Order Constrained Optimization in Policy Space, NeurIPS (spotlight paper), 2020.
3. Xinyue Chen, Zijian Zhou, Zheng Wang, Che Wang, Yanqiu Wu, Keith Ross, Best Action Imitation Learning for Batch Reinforcement Learning, NeurIPS 2020.
4. Che Wang, Yanqiu Wu, Quan Vuong, Keith Ross, Towards Simplicity in Deep Reinforcement Learning: Streamlined Off-Policy Learning, International Conference on Machine Learning (ICML), 2020.
5. Quan Vuong, Yiming Zhang, Keith W. Ross, Supervised Policy Update for Deep Reinforcement Learning, International Conference on Learning Representations (ICLR), 2019.
My current research focuses on spoken dialog systems, including task-oriented dialogue modeling, question and answering, and chit-chat bots. My ultimate research goal is to design virtual personal assistants that will become smarter over time. They can acquire new knowledge from various text sources and through interaction, teaching, and feedback from humans.
1. Y. C. Tam, J. Ding, C. Niu and J. Zhou, Cluster-based Beam Search for Pointer- Generator Chatbot Grounded by Knowledge (DSTC7 track 2 winner), Computer Speech Language, volume 64, Elsevier, 2020.
2. Z. Liu, Z. Fu, J. Cao, G. Melo, Y. C. Tam, C. Niu, J. Zhou, Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation, ACL 2019.
3. S. Sun, Y. C. Tam, J. Cao, C. Yan, Z. Fu, C. Niu and J. Zhou, End-to-end Gated Self-attentive Memory Network for Dialog Response Selection (won the second place on one sub-task of response selection track), Dialog System Technology Challenges (DSTC7) 2019.
4. H. Deng and Y. C. Tam, Read and Comprehend by Gated-Attention Reader with More Belief, NAACL 2018.
5. Y. C. Tam and Y. Shi and H. Chen and M. Y. Hwang, RNN-Based Labeled Data Generation for Spoken Language Understanding, Proceedings of Interspeech, Dresden, Germany, 2015.
I am broadly interested in the design of interactive intelligent systems to extend human musical creation and expression. This research lies in the intersection of Machine Learning, HCI, Robotics, and Computer Music.
1. Ziyu Wang, Dingsu Wang, Yixiao Zhang, Gus Xia, Learning Interpretable Representation for Controllable Polyphonic Music Generation, International Society for Music Information Retrieval (ISMIR) 2020.
2. Ziyu Wang, Yiyi Zhang, Yixiao Zhang, Junyan Jiang, Ruihan Yang, Junbo Zhao, Gus Xia, PIANOTREE VAE: Structured Representation Learning for Polyphonic Music, International Society for Music Information Retrieval (ISMIR) 2020.
3. Ziyu Wang*, Ke Chen*, Junyan Jiang, Yiyi Zhang, Maoran Xu, Shuqi Dai, Xianbin Gu, Gus Xia, POP909: A Pop-song Dataset for Music Arrangement Generation, International Society for Music Information Retrieval (ISMIR) 2020.
4. Daniel Chin, Yian Zhang, Tianyu Zhang, Jake Zhao, Gus G Xia, Interactive Rainbow Score: A Visual-centered Multimodal Flute Tutoring System, International Conference on New Interfaces for Musical Expression (NIME) 2020.
5. Junyan Jiang, Gus G Xia, Dave B Carlton, Chris N Anderson, Ryan H Miyakawa, Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning, International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020.