Yang Zhang

My research focuses on the Human-centered Artificial Intelligence (AI) and Social Sensing. In particular, my research aims to explicitly utilize the human intelligence from crowdsourcing systems (i.e., crowd intelligence) to effectively design, configure, and troubleshoot the AI models to improve the performance, fairness, explainability, and accountability of the AI models in social sensing applications. I am delighted to design principled solutions that integrate the state-of-the-art crowdsourcing techniques (e.g., Amazon MTurk), AI models (e.g., convolutional/recurrent/graph neural network, generative adversarial network, transfer/contrastive learning), and estimation theoretical approaches (e.g., maximum likelihood estimation (MLE), subjective logic) to jointly model the diversified yet complementary AI and crowd intelligence to address a rich set of complex real-world problems including urban infrastructure monitoring, disaster damage assessment, traffic risk prediction, misinformation detection, etc.

• Best Paper Award, ACM/IEEE ASONAM 2022
• Best Paper Honorable Mention, IEEE SMARTCOMP 2022
• Outstanding Graduate Research Assistant Award, University of Notre Dame
• Video Presentation Award, ACM/IEEE IWQoS 2020
• W. J. Cody Associates, Argonne National Laboratory
• IEEE Student Travel Award, IEEE BigData 2019
• IEEE Student Travel Award, IEEE BigData 2018
• Data Science Scholar Fellowship, Indiana University
• First Class Scholarship, Wuhan University

Y. Zhang, Z. Kou, L. Shang, H. Zhen, Z. Yue, and D. Wang. A Crowd-AI Duo Relational Graph Learning Framework Towards Social Impact Aware Photo Classification. Proceedings of Thirty-Seven AAAI Conference on Artificial Intelligence (AAAI), 2023, Washington, DC, 2023. [Acceptance Rate: 19.6%]

Y. Zhang, R. Zong, L. Shang, Z. Kou, and D. Wang. An Active One-Shot Learning Approach to Recognizing Land Usage from Class-wise Sparse Satellite Imagery in Smart Urban Sensing. Elsevier Knowledge- Based Systems (KBS). [Impact Factor: 8.038]

Y. Zhang, R. Zong, L. Shang, and D. Wang. On Coupling Classification and Super-Resolution in Remote Urban Sensing: An Integrated Deep Learning Approach: A Deep Duo-Task Learning Approach. IEEE Transactions on Geoscience and Remote Sensing (TGRS). [Impact Factor: 5.6]

Y. Zhang, R. Zong, L. Shang, Z. Kou, and D. Wang. CrowdNAS: A Crowd-guided Neural Architecture Searching Approach to Disaster Damage Assessment. In Proceedings of the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Virtual Conference, 2022

Y. Zhang, R. Zong, L. Shang, Z. Kou, H. Zeng, and D. Wang. CrowdOptim: A Crowd-driven Neural Network Hyperparameter Optimization Approach to AI-based Smart Urban Sensing. Proceedings of the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). Virtual Conference, 2022

Y. Zhang, L Shang, R. Zong, Z. Wang, Z. Kou, and D. Wang. StreamCollab: A Streaming Crowd-AI Collaborative System to Smart Urban Infrastructure Monitoring in Social Sensing. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing (HCOMP), Virtual Conference, 2021. [Acceptance Rate: 26.0%]

Y. Zhang, R. Zong, Z. Kou, L. Shang, and D. Wang. On Streaming Disaster Damage Assessment in Social Sensing: A Crowd-driven Dynamic Neural Architecture Searching Approach. Elsevier Knowledge-Based Systems (KBS). [Impact Factor: 8.038]

Y. Zhang, R. Zong, Z. Kou, L. Shang, and D. Wang. CollabLearn: An Uncertainty-Aware Crowd-AI Collaboration System for Cultural Heritage Damage Assessment. IEEE Transactions on Computational Social Systems (TCSS). [Impact Factor: 5.357]