Associate Professor
Department of Computer Science
Emory University

Research Interests

Deep learning on graphs

Societal event prediction

Interpretable machine learning

Spatio-temporal data mining

Deep generative models

Social media mining

Nonconvex Optimization

Liang Zhao

Dr. Liang Zhao is an associate professor at the Department of Computer Science at Emory University. He was an assistant professor at the Department of IST and CS at George Mason University. He obtained his Ph.D. degree as an Outstanding Doctoral Student in the Department of Computer Science at Virginia Tech in 2017. His research interests include data mining, artificial intelligence, and machine learning, with special interests in spatiotemporal and network data mining, deep learning on graphs, nonconvex optimization, and interpretable machine learning.

He has published over a hundred papers in top-tier conferences and journals such as KDD, ICDM, TKDE, NeurIPS, Proceedings of the IEEE, TKDD, TSAS, IJCAI, AAAI, WWW, CIKM, SIGSPATIAL, and SDM. He won NSF CAREER Award in 2020. He has also won Cisco Faculty Research Award in 2023, Meta Research Award in 2022, Amazon Research Award in 2020, and Jeffress Trust Award in 2019, , and was ranked as one of the "Top 20 Rising Star in Data Mining" by Microsoft Search in 2016. He has won best paper award in ICDM 2022, best poster runner-up in ACM SIGSPATIAL 2022, Best Paper Award Shortlist in WWW 2021, Best Paper Candidate in ACM SIGSPATIAL 2022, Best Paper Award in ICDM 2019, and best paper candidate in ICDM 2021. He is recognized as "Computing Innovative Fellow Mentor" in 2021 by Computing Research Association. He is a senior member of IEEE.

My group is constantly searching for highly-motivated students. Those who are interested are encouraged to contact me: liang.zhao_at_emory_dot_edu.

Selected Recent Topics

Multimodal Explanation-guided Learning: Evaluating and Correcting the Reasoning of AI models.

Datasets for Benchmarking XAI on Images: [Website]

Datasets for Benchmarking XAI on Graphs: [ChemRxiv]

Explanation Supervision on Images: [KDD 2022][CSCW 2022][ICCV 2023][KDD 2023]

Explanation Supervision on 3D Images: [KDD 2022][CSCW 2024][KDD 2024]

Explanation Supervision on Graphs: [ICDM 2021]

Explanation Active Learning on Texts: [ACL 2024]

Explanation Prompting on Images: [IJCAI 2024]

Systematic Review: [CSUR]

Structure-guided Representation Learning: Disentangling Latent Features by Their Structural Semantics.

General Graphs: [KDD 2020]

Spatial Graphs: [KDD 2022][NeurIPS 2021]

Dynamic Graphs: [SDM 2021][WWW 2021]

Periodic Graphs: [NeurIPS 2022]

Spatiotemporal Graphs: [PKDD 2022][AAAI 2022]

Trajectories: [SIGSPATIAL 2022, Best Paper Candidate]

Polygons: [KDD 2024]

Geometric Trees: [KDD 2024]

Controllable Data Generation: Generate New Data with Desired Properties' Values

Independent Properties: [ICLR 2021]

Correlated Properties: [NeurIPS 2022]

Datasets for Benchmarking Data Generation: [Website][NeurIPS 2021]

Survey Papers: [TPAMI][CSUR]

Graph Neural Networks for Data Mining: Reframing Classic Data Mining with Gradient Descent.

Graph Outlier Detection [ICDM 2022, Best Paper Award]

Clustering: [Preprint]

Network Interdiction: [preprint]

Influence Maximization: [ICML 2023][AISTATS 2024]

Source Localization: [KDD 2022][WWW 2022][KDD2024]

Synergize Large Language Models and Graph Mining: Transformation Between Structures and Semantics

Text-attributed graph: [preprint][CIKM 2024]

Trajectory mining: [preprint]

Edge-text graph: [NeurIPS 2024]

Graph Retrival Augmented Generation: GRAG [paper]

Link prediction: [NeurIPS GLFrontiers 2023][ICDM 2024]

Survey on Domain Specialization: [preprint]

Accelerating Large Language Models

Model Pruning: SparseLLM [NeurIPS 2024]

Knowlege Distillation: [ACL 2024]

Survey on Resource-efficient LLMs: [preprint][Website]

Temporal Domain Generalization

Discrete time: SparseLLM [ICLR 2023, oral]

Continuous time: [NeurIPS 2024]

---

---

---