Rate My Professor Daokun Zhang

Dr. Zhang's research focuses on graph machine learning, including graph representation learning, graph structure learning, node classification, link prediction, weakly supervised learning with sparse or noisy labels, and uncertainty quantification in machine learning predictions. His interests also encompass network analysis, knowledge graphs, and applications in knowledge graph completion and alignment, combinatorial optimization, computational drug discovery and materials science, particle system simulation, and geographic data forecasting. He has authored numerous publications in leading venues. Key works include Network representation learning: A survey (IEEE Transactions on Big Data, 2020), Towards unsupervised deep graph structure learning (The Web Conference, WWW 2022), Link prediction with contextualized self-supervision (IEEE Transactions on Knowledge and Data Engineering, 2023), GraphormerDTI: A graph transformer-based approach for drug-target interaction prediction (Computers in Biology and Medicine, 2024), Graph Neural Network-Based Molecular Property Prediction with Patch Aggregation (Journal of Chemical Theory and Computation, 2024), and Towards complex dynamic physics system simulation with graph neural ordinary equations (Neural Networks, 2024). Additional contributions appear in conferences such as AAAI, ICDM, PAKDD, and journals including Expert Systems with Applications, Engineering Geology, and Data Mining and Knowledge Discovery.