Ping Xiong
Ping Xiong
Doctoral Researcher
Affiliation: BIFOLD
- M.Sc. Industrial Engineering, TU Berlin
- B.Sc. Industrial Engineering, TU Berlin
- Member of BIFOLD Graduate School
- Explainable AI
- Graph Neural Network
- Bayesian Learning Applications
Junyou Zhu, Langzhou He, Fenying Cai, Christian Nauck, Ping Xiong, Chao Gao, Philip S. Yu, Klaus-Robert Müller, Jürgen Kurths, Frank Hellmann
Stability-Shaped Deep Graph Learning
Ping Xiong, Shanglin Li, Yi Ding, Thomas Schnake, Shinichi Nakajima
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
Ping Xiong, Thomas Schnake, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
Haci Ismail Aslan, Philipp Wiesner, Ping Xiong, Odej Kao
β-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation
Haci Ismail Aslan, Philipp Wiesner, Ping Xiong, Odej Kao
-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation
Symbolic XAI
Researchers at BIFOLD have been exploring how to make AI explain itself in the same way, people explain themselves. The team’s work focuses on making AI predictions as clear and intuitive as a human explanation.