MPI-INF Logo
Azin Ghazimatin

About

Azin Ghazimatin completed her PhD at the Max Planck Institute for Informatics. Her research focuses on Transparency and Explanainability of Recommender Systems. She received her master’s degree at Sharif University of Technology and her bachelor’s at Amirkabir University of Technology, Tehran, Iran.

This page will no longer be updated. Please visit my new homepage.

Research Interests

  • Explainable AI
  • Recommender Systems
  • Human-in-the-Loop Machine Learning
  • Social Network Analysis
  • Combinatorial Optimization

News

  • December 2021: Defended my PhD with a summa cum laude!
  • August 2021: Starting a research internship at Amazon, Berlin
  • 19-23 April 2021: The Web Conference, Online Event
  • 25-30 July 2020: SIGIR Conference, Online Event
  • Oct 2019-Feb 2020: Coordinator for course "Information Retrieval and Data Mining", Saaland University
  • 11-15 February 2019: WSDM Conference, Melbourne, Australia
  • 27 August 2018 - 08 September 2018: Machine Learning Summer School (MLSS), Madrid, Spain
  • Oct 2017-Feb 2018: TA for "Information Retrieval and Data Mining", Saaland University

Publications

  • Enhancing Explainability and Scrutability of Recommender Systems
    Azin Ghazimatin
    PhD Thesis
    [PDF]

  • Counterfactual Explanations for Neural Recommenders
    Khanh Hiep Tran, Azin Ghazimatin and Rishiraj Saha Roy
    44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)
    [PDF][Code][Video]

  • ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models
    Azin Ghazimatin, Soumajit Pramanik, Rishiraj Saha Roy, and Gerhard Weikum
    30th The Web Conference 2021
    [PDF] [Video] [Code and Data]

  • Explaining Recommendations in Heterogeneous Networks
    Azin Ghazimatin
    43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020)
    Doctoral Consortium
    [PDF]

  • PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems
    Azin Ghazimatin, Oana Balalau, Rishiraj Saha Roy, and Gerhard Weikum
    13th ACM International Conference on Web Search and Data Mining (WSDM 2020)
    [PDF] [Slides] [Poster] [Code]

  • FAIRY: A Framework for Understanding Relationships between Users’ Actions and their Social Feeds
    Azin Ghazimatin, Rishiraj Saha Roy, Gerhard Weikum
    12th ACM International Conference on Web Search and Data Mining (WSDM 2019)
    [PDF] [Slides] [Poster] [Code]

  • Learning to Un-Rank: Quantifying Search Exposure for Users in Online Communities
    Asia J. Biega, Azin Ghazimatin, Hakan Ferhatosmanoglu, Krishna Gummadi, Gerhard Weikum
    26th ACM International Conference on Information and Knowledge Management (CIKM 2017)
    [PDF]

  • Team Selection for Prediction Tasks
    MohammadAmin Fazli, Azin Ghazimatin, Jafar Habibi, Hamid Haghshenas
    Journal of Combinatorial Optimization, Springer 2014
    [PDF]

Teaching

  • Information Retrieval and Data Mining (Coordinator), Saarland University, winter semester 2019-2020
  • Information Retrieval and Data Mining (TA), Saarland University, winter semester 2017-2018
  • Discrete-Event System Simulation (TA), Sharif University, summer semester 2014

Recent Positions

  • August 2021 - February 2022
    Applied scientist intern at Amazon, Berlin, Germany
  • September 2016 - February 2017
    Research assistant at Max Planck Institute for Software Systems, Saarbrücken, Germany
  • November 2015 - February 2017
    Saarbrücken Graduate School of Computer Science, Germany

Education

  • March 2017 - December 2021: Max-Planck-Institut für Informatik, Saarbrücken, Germany. Ph.D. in Computer Science.
  • September 2012 - August 2014: Sharif University of Technology, Tehran, Iran. M.Sc. in Softwares and Systems.
  • September 2008 - September 2012: Amirkabir University of Technology, Tehran, Iran. B.Sc. in Software Engineering.