Liang Zhao

Liang Zhao is a computer scientist and academic. He is an associate professor in the Department of Compute Science at Emory University.

Zhao's research focuses on data mining, machine learning, and artificial intelligence, with particular interests in deep learning on graphs, societal event prediction, interpretable machine learning, multi-modal machine learning, generative AI, and distributed deep learning. His book titled Graph Neural Networks: Foundations, Frontiers, and Applications has been published by Springer. He published articles in journals and conferences, some of which have won Best Paper Awards. Zhao received the Oracle for Research Grant Award, Cisco Faculty Research Award, Amazon Research Award and Meta Research Award. He also won the Jeffress Trust Award for deep generative models for biomedical research, and the NSF Career Award for his research on explainable and interactive AI for spatial and graph data.

Zhao was a Computing Innovation Fellow Mentor for the Computing Community Consortium and is an IEEE Senior Member.

Education
Zhao earned his Bachelor of Science in Automation and then obtained a Master of Science in Control Theory and Control Engineering from Northeastern University graduating from there in 2012. He completed his Ph.D. in Computer Science at Virginia Polytechnic Institute and State University in 2016.

Career
Zhao began his career as an assistant professor in the Departments of Information Science and Technology and Computer Science at George Mason University in 2016, the same year he was named as one of the Top 20 Rising Stars in Data Mining by Microsoft Academic Search. He served as an assistant professor in the Department of Computer Science at Emory University from 2020 to 2023 and has been serving as an associate professor since then.

Research
Zhao has focused his research on advancing data mining, machine learning and AI techniques, particularly their applications to critical real-world problems. His interests encompass intelligent learning strategies, scalable optimization methods, and modeling text data to develop solutions for open and critical real-world issues through research.

Generative AI on complex data
Zhao has conducted research on complex data deep modeling, focusing on spatial, temporal, networked, textual, and heterogeneous types. He advanced new graph neural networks and inference strategies to encode complex data into their components, enabling independent and combined learning of their embeddings. To contribute to the deep graph learning research domain, he published Graph Neural Networks: Foundations, Frontiers, and Applications with Jian Pei, Peng Cui, and Lingfei Wu which covered a range of topics in deep learning on graphs.

Zhao jointly characterized the distributions of temporal and network aspects using new techniques in temporal random walk generation and end-to-end walk assembly. His contributions include creating deep generative models for spatial networks that identify the interplay between spatial and network factors, as well as factors related solely to spatial or network information. Further enhancing deep graph transformation, which generated target graphs conditioned on source graphs, he used applications such as molecule structure optimization and circuit obfuscation with his work on deep generative models for graphs extending into several directions, including property-controllable complex data generation and design. While addressing the critical need for unique datasets and model evaluation strategies in deep generative models, he released benchmark dataset repositories such as GraphGT at NeurIPS 2021, along with review papers on the method categorization and standardization.

Collaborative machine learning strategies
Zhao focused on developing models for learning and predicting across both known and unknown tasks. His research introduced directions in spatial multi-task learning, balancing the trade-offs between task relations and differences, as well as spatial correlation and heterogeneity. Beyond traditional approaches, he extended multi-task learning frameworks into domain generalization scenarios, allowing models trained on known tasks to generalize to unseen tasks across different locations and times. He then conducted research on continual learning integrated temporal considerations to manage the persistence and adaptability of a model's memory across old and new tasks, drawing insights from neuroscience principles of memory retention to achieve high accuracy with low computational costs.

Human-AI interaction and alignment
Zhao investigated explainable AI, particularly AI reasoning and its correction through human guidance, to improve medical imaging for disease diagnosis by developing techniques, benchmarks, and evaluation scenarios in collaboration with radiologists and clinicians. He focused on proposing methods that narrow the distributional gaps between humans and AI's explanations in complex data such as 2D/3D images, graphs, and spatiotemporal data  which can benefit both training and promotion of AI models. Additionally, his team developed and deployed user interface systems that enables the online interaction between human and AI.

Awards and honors

 * 2020 – NSF CAREER Award, National Science Foundation
 * 2020 – Amazon Research Award, Amazon Science
 * 2022 – Meta Research Award, Meta Platform

Selected books

 * Graph Neural Networks: Foundations, Frontiers, and Applications (2022) ISBN 978–9811660566

Selected articles

 * Zhao, L. (2021). Event prediction in the big data era: A systematic survey. ACM Computing Surveys (CSUR), 54(5), 1-37.
 * Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., ... & Zhao, L. (2023). Domain specialization as the key to make large language models disruptive: A comprehensive survey. arXiv preprint arXiv:2305.18703.
 * Zhao, L., Sun, Q., Ye, J., Chen, F., Lu, C. T., & Ramakrishnan, N. (2015). Multi-task learning for spatio-temporal event forecasting. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1503–1512).
 * Chai, Z., Chen, Y., Anwar, A., Zhao, L., Cheng, Y., & Rangwala, H. (2021). FedAT: A high-performance and communication-efficient federated learning system with asynchronous tiers. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 1–16).
 * Ling, C., Jiang, J., Wang, J., Thai, M. T., Xue, R., Song, J., ... & Zhao, L. (2023). Deep graph representation learning and optimization for influence maximization. In International Conference on Machine Learning (pp. 21350–21361). PMLR.