Ping Xiong

Ping Xiong is a Researcher at the Berlin Institute for the Foundations of Learning and Data (BIFOLD), Technical University of Berlin. His academic background includes a Ph.D. in Industrial Engineering (2022–present), and both M.Sc. and B.Sc. degrees in Industrial Engineering from TU Berlin (2017–2022).

Research interests focus on Explainable AI (XAI), Bayesian Learning, and applications in Machine Learning and Graph Neural Networks. He explores symbolic explanations, logical feature relationships, and robust ensemble methods against adversarial perturbations in graph structures.

His recent work emphasizes efficient computation techniques for subgraph attribution and interpretable GNNs. Notable contributions include studies on β-GNN robustness and walk-based explanation methods for GNNs.

Affiliated with BIFOLD Graduate School, his work bridges theoretical advancements in machine learning with practical interpretability challenges. No awards or grants explicitly mentioned, but active in publishing cutting-edge research in XAI and graph learning domains.