Sadegh Akhondzadeh

myimg.jpg

Universität zu Köln Abteilung Informatik

Sibille-Hartmann-Str. 2-8

50969 Köln Deutschland

Hi, I’m Sadegh 👋. I’m a PhD student at the University of Cologne, fortunate to be advised by Dr. Aleksandar Bojchevski. During my PhD, I completed an internship at Axelera AI. Before that, I worked as a research assistant at CISPA and completed my master’s degree at Saarland University.

My current research focuses on trustworthy machine learning and efficient machine learning.

I’m always open to collaboration and new opportunities—feel free to reach out via email!

news

May 01, 2024 Our paper on robust conformal prediction was accepted at ICML 2024.
Feb 01, 2024 Our paper titled Rethinking Label Poisoning for GNNs: Pitfalls and Attacks accpeted at ICLR 2024.
Jan 15, 2024 I joined Axelera AI as a Research Intern.
Jan 21, 2023 Our paper on probing the representation of graph-based models was accepted at AISTATS.
Nov 16, 2022 I will be presenting our new preprint, titled Probing Graph Representation for Molecules, at the ELLIS ML4Molecules Workshop.

selected publications

  1. AISTATS
    Probing Graph Representation
    Mohammad Sadegh Akhondzadeh, Vijay Lingam, and Aleksandar Bojchevski
    In International Conference on Artificial Intelligence and Statistics AISTATS, 2022
  2. ICLR
    Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
    Vijay Lingam, Mohammad Sadegh Akhondzadeh, and Aleksandar Bojchevski
    In The Twelfth International Conference on Learning Representations, ICLR, 2024
  3. WEBSCI 2021
    Wide-AdGraph: Detecting Ad Trackers with a Wide Dependency Chain Graph
    Amir Hossein Kargaran, Mohammad Sadegh Akhondzadeh, Mohammad Reza Heidarpour, and 3 more authors
    In 13th ACM Web Science Conference, 2021
  4. ICML
    Robust Yet Efficient Conformal Prediction Sets
    Soroush H Zargarbashi, Mohammad Sadegh Akhondzadeh, and Aleksandar Bojchevski
    In International Conference on Machine Learning, ICML, 2024