Welcome to my homepage! I am a third-year Ph.D. candidate in the Machine Learning Group at the Department of Computer Science, Technische Universität Berlin, Germany, supervised by Prof. Klaus-Robert Müller and Prof. Jürgen Kurths. In parallel, I am a doctoral researcher at the Potsdam Institute for Climate Impact Research (PIK), working under the guidance of Dr. Frank Hellmann.
My research focuses on graph machine learning and machine learning for climate science. Current topics include:
- Graph Representation Learning: theoretical and methodological aspects of node classification, link prediction, and graph classification.
- Machine Learning for Climate Science: using machine learning to better understand and anticipate changes in climate extremes under global warming, and to assess their impacts, with a particular focus on extreme heat events. Please feel free to contact me if you are interested in potential research collaborations.
🔥 News
- 05.2026: 🎉🎉 One paper on landscapes learning for synchronization networks was accepted to ICML 2026!
- 04.2026: 🎉🎉 One paper on robust graph learning for fake news detection was accepted to IEEE TKDE!
- 10.2025: 🎉🎉 One paper on AI for power grids was accepted to IEEE TKDE!
- 05.2025: 🎉🎉 One paper on graph representation learning was accepted to ICML 2025!
- 04.2025: I have officially joined the ‘Explainable AI for Dynamic Stability Assessment’ project at PIK!
- 05.2024: 🎉🎉 One paper on graph-based fake news detection was accepted to KDD 2024!
📝 Selected Publications
* Corresponding author.
Learning Dynamic Stability Landscapes in Synchronization Networks
Christian Nauck, Junyou Zhu*, Michael Lindner, Frank Hellmann
In Proceedings of the 43rd International Conference on Machine Learning. (ICML 2026)
Network Measure-Enriched GNNs: A New Framework for Power Grid Stability Prediction
Junyou Zhu, Christian Nauck, Michael Lindner, Langzhou He, Philip S Yu, Klaus-Robert Müller, Jürgen Kurths, Frank Hellmann
IEEE Transactions on Knowledge and Data Engineering 38.1 (2025): 518-531. (IEEE TKDE)
SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning
Junyou Zhu, Langzhou He, Chao Gao, Zhen Su, Philip S. Yu, Jürgen Kurths, Frank Hellmann
In Proceedings of the 42nd International Conference on Machine Learning. (ICML 2025)
Propagation Structure-Aware Graph Transformer for Robust and Interpretable Fake News Detection
Junyou Zhu, Chao Gao, Ze Yin, Xianghua Li, Jürgen Kurths
In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (KDD 2024)
Community Detection in Graph: An Embedding Method
Junyou Zhu, Chunyu Wang, Chao Gao, Fan Zhang, Zhen Wang, Xuelong Li
IEEE Transactions on Network Science and Engineering 9.2 (2022): 689-702. (IEEE TNSE)
Unsupervised Community Detection In Attributed Networks Based On Mutual Information Maximization
Junyou Zhu, Xianghua Li, Chao Gao, Zhen Wang, Jürgen Kurths
New Journal of Physics 23.11 (2021): 113016. (NJP)
Unsupervised Dynamic Network Embedding Using Global Information
Junyou Zhu, Zheng Luo, Fan Zhang, Haiqiang Wang, Jiaxin Wang, Chao Gao
In 2021 International Joint Conference on Neural Networks. (IJCNN 2021)
👔 Work Experience
04.2025 - 12.2027, Researcher at Department of Complexity Science, Potsdam Institute for Climate Impact Research.
14473 Potsdam, Germany
03.2023 - 03.2025, Guest Researcher at Department of Complexity Science, Potsdam Institute for Climate Impact Research.
14473 Potsdam, Germany
🔍 Reviewer Service
- IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE)
- IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
- IEEE Transactions on Network Science and Engineering (IEEE TNSE)
- IEEE Transactions on Emerging Topics in Computing (IEEE TETC)
- CAAI Transactions on Intelligence Technology (CAAI TIT)
- ICLR 2026
- ICML 2026; ICML 2025
- NeurIPS 2024
- KDD 2024
Welcome!
Thanks for stopping by — it’s lovely to have you here.
Around ... visitors so far
... page views
