Lu Lin (林璐)

:wave: Bio: Hi, I’m Lu. I am currently a tenure-track assistant professor in the College of Information Sciences and Technology, Penn State University starting 2022 Fall. Prior to that, I received my Ph.D. in Computer Science at University of Virginia in 2022, under supervision of Dr. Hongning Wang. I recieved my M.s. and B.S. in 2017 and 2014 respectively, from Computer Science at Beihang University. I have also interned at Didi Lab, LinkedIn and Pinterest Lab.

:pushpin: Research interests: I have a broad interest in machine learning and data mining. My current focus is practical and trustworthy machine learning on graph-structured data, concerning multiple aspects including robustness, fairness, interpretability and privacy. To be more specific:

  • machine learning on graphs, e.g. graph neural networks, graph representation learning
  • trustworthy machine learning, w.r.t. adversarial robustness, fairness, interpretability, privacy
  • data mining and data science in real-world applications

:fire: Openings: I’m looking for highly motivated students, including PhDs (fully-funded), Masters, undergraduates, and interns to join my group. If you’re interested in working with me, please don’t hesitate to drop me an email (lulin[at]psu[dot]edu) with your CV. Please check Open Position for more details.

News

Sep 22 :rocket: I am officially on board as a tenure-track faculty at IST@PSU. Multiple open positions available!
Jun 22 :mortar_board: I passed my dissertation defense!
May 22 :pushpin: Our paper on graph structural attack by perturbing spectrum was accepted by KDD 2022.
May 22 :pushpin: Our paper on communication-efficient adaptive federated learning was accepted by ICML 2022.
May 22 :rocket: I am honored to receive CS John A. Stankovic Graduate Research Award from UVa
Feb 22 :microphone: I gave a talk on Graph Structure as A Double-Edged Sword in Machine Learning at IST@PSU.
Feb 22 :microphone: I gave a talk on Graph Structure as A Double-Edged Sword in Machine Learning at DS@NJIT.
Feb 22 :microphone: I gave a talk on Graph Structure as A Double-Edged Sword in Machine Learning at CS@WM.
Feb 22 :pushpin: Our paper on communication-efficient adaptive gradient method was accepted by AISTATS 2022.
Jan 22 :pushpin: Our paper on unbiased graph embedding from biased topology was accepted by WWW 2022.

Selected Publications [full list]

  1. KDD
    Graph Structural Attack by Perturbing Spectral Distance
    Lu Lin, Ethan Blaser, and Hongning Wang
    Proceedings of the 28th ACM SIGKDD international conference on knowledge discovery & data mining, KDD 2022
  2. ICML
    Communication-Efficient Adaptive Federated Learning
    Yujia Wang, Lu Lin, and Jinghui Chen
    Proceedings of the 39th International Conference on Machine Learning, ICML 2022
  3. AISTATS
    Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
    Yujia Wang, Lu Lin, and Jinghui Chen
    Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, AISTATS 2022
  4. WWW
    Unbiased Graph Embedding with Biased Graph Observations
    Nan Wang*, Lu Lin*, Jundong Li, and Hongning Wang
    Proceedings of the Web Conference, WWW 2022
  5. KDD
    Graph Attention Networks over Edge Content-based Channels
    Lu Lin, and Hongning Wang
    In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, KDD 2020
  6. TKDE
    Road Traffic Speed Prediction: A Probabilistic Model Fusing Multi-source Data
    Lu Lin, Jianxin Li, Feng Chen, Jieping Ye, and Jinpeng Huai
    IEEE Transactions on Knowledge and Data Engineering, TKDE 2017