Graph Representation Learning

Representation learning on graphs enables downstream tasks such as graph classification and link prediction in multiple application scenarios. We design novel graph representation learning pipelines to achieve state-of-the-art performance on these downstream tasks, leveraging tools such as random-walks, social theories, graph neural networks, and bilevel optimization. We also investigate the explainability of graph representation learning models, which is vital, especially in high-stakes applications such as drug discovery and anomaly detection.

Affiliated People

Photo of Zexi Huang.
Research interests: 

Graph Data Mining, Representation Learning

Zexi received his B.Eng. in Computer Science and Technology at University of Electronic Science and Technology of China, Chengdu in 2018. He joined Dynamo lab in 2018. His research interests span the analysis of social, informational, and biological networks with machine learning and data mining techniques. 

Research interests: 

Data Mining, Applied Machine Learning, Network Science.

Mert received a B.Sc in Computer Science and Engineering in 2018 from Sabanci University, Istanbul. He joined Dynamo lab as a Ph.D. student in 2018. His research interests include machine learning on graphs, explainability, and human-ai interactions. He is exploring novel graph neural network algorithms to solve graph tasks such as graph classification and link prediction on the different types of networks like social, communication, and molecular. He previously worked on differential privacy on recommendation systems using graph data in his bachelor's.