Bonjour! こんにちは！

I’m Mark (Junchen) Jin, a Machine Learning Scientist at PayPal. Currently I’m working on projects related to personalization, knowledge graph, and GenAI.

I graduated from the Master of Science in Machine Learning and Data Science (formerly MSiA) program at the Northwestern University. Prior to this, I obtained my dual bachelor’s degrees in Computer Science from the University of Michigan, Ann Arbor, and in Electrical and Computer Engineering from Shanghai Jiao Tong University.

I’ve been conducting research in graph mining, data mining, and applied machine learning, especially on graph representation learning and graph neural networks.

Publications

2022

• Jiong Zhu, Junchen Jin, Donald Loveland, Michael T Schaub, and Danai Koutra. 2022. How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22).
  [ Paper ] [ Code ]

2021

• Junchen Jin, Mark Heimann, Di Jin, and Danai Koutra. 2021. Toward Understanding and Evaluating Structural Node Embeddings. ACM Transactions on Knowledge Discovery from Data 16, 3 (November 2021).
  [ Paper ] [ Code ]

2020

• Junchen Jin, Mark Heimann, Di Jin, and Danai Koutra. 2020. Understanding and evaluating structural node embedding’s. In KDD MLG Workshop.
  [ Paper ]