Professor
Ruhr University Bochum
Research Center for Trustworthy Data Science and Security
Email: bilal.zafar@rub.de
About
I am a professor of Computer Science at Ruhr University Bochum and Research Center for Trustworthy Data Science and Security. I am also a PI at the Cluster of Excellence CASA and a member of the Horst Görtz Institute for IT Security.
Previously I was a Senior Applied Scientist at Amazon Web Services (AWS) in Berlin, Germany where I was building products to support trustworthy use of Artificial Intelligence (AI) and Machine Learning (ML). Before joining AWS, I was a Research Scientist at Bosch Center for Artificial Intelligence in Renningen, Germany. I did my PhD at Max Planck Institute for Software Systems (MPI-SWS) and Saarland University. I was co-advised by Krishna P. Gummadi and Manuel Gomez Rodriguez.
Job openings
I have several openings in my group. If you are interested in a PhD position and have background in one of Computer Science, Mathematics, Statistics, Natural Language Processing, Artificial Intelligence and Machine Learning, drop me an email. If you are a student at RUB and would like to pursue your Bachelor’s or Master’s thesis with me, please reach out.
Research interests
My research interests are in the area of human-centric AI/ML. My work aims to address challenges that arise when AI/ML models interact with human users. For instance, I develop algorithms for making AI/ML models more fair, explainable and robust. For more details, see my Google Scholar profile.
Publications
-
On the Lack of Robust Interpretability of Neural Text Classifiers
M. B. Zafar, M. Donini, D. Slack, C. Archambeau, S. Das, K. Kenthapadi
ACL Findings 2021.
[PDF] -
Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
M. Hardt, X. Chen, X. Cheng, M. Donini, J. Gelman, S. Gollaprolu, J. He, P. Larroy, X. Liu, N. McCarthy, A. Rathi, S. Rees, A. Siva, E. Tsai, K. Vasist, P. Yilmaz, M. B. Zafar, S. Das, K. Haas, T. Hill, K. Kenthapadi
KDD 2021.
[PDF] -
Fair Bayesian Optimization
V. Perrone, M. Donini, M. B. Zafar, K. Kenthapadi and C. Archambeau
AIES 2021.
[PDF] -
Multi-Objective Multi-Fidelity Hyperparameter Optimization with Application to Fairness
R. Schmucker, M. Donini, V. Perrone, M. B. Zafar and C. Archambeau
NeurIPS 2020 Meta-Learning Workshop.
[PDF] -
Counterfactual Accuracies for Alternative Models
U. Bhatt, M. B. Zafar, K. P. Gummadi and A. Weller
ICLR 2020 Workshop on Machine Learning in Real Life.
[PDF] -
Unifying Model Explainability and Robustness via Reasoning Labels
V. Nanda, J. Ali, K. P. Gummadi and M. B. Zafar
NeurIPS 2019 Safety and Robustness in Decision Making (SRDM) Workshop.
[PDF] -
Fairness Constraints: A Flexible Approach for Fair Classification
M. B. Zafar, I. Valera, M. Gomez Rodriguez and K. P. Gummadi
JMLR, 2019.
[PDF] -
Loss-Aversively Fair Classification
J. Ali, M. B. Zafar, K. P. Gummadi and A. Singla
AIES 2019, Honolulu, HI, January 2019.
[PDF] -
Search Bias Quantification: Investigating Political Bias in Social Media and Web Search
J. Kulshrestha, M. Eslami, J. Messias, M. B. Zafar, S. Ghosh, K. P. Gummadi, K. Karahalios
Information Retrieval Journal, 2019.
[PDF]
-
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual &Group Unfairness via Inequality Indices
T. Speicher, H. Heidari, N. Grgić-Hlača, K. P. Gummadi, A. Singla, A. Weller and M. B. Zafar
KDD 2018, London, UK, August 2018.
[arXiv] -
Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
N. Grgić-Hlača, M. B. Zafar, K. P. Gummadi and A. Weller
AAAI 2018, New Orleans, LA, February 2018.
[PDF]
Also presented at NIPS Symposium on ML and the Law 2016, Barcelona, Spain, December 2016. (Notable Paper Award)
-
From Parity to Preference-based Notions of Fairness in Classification
M. B. Zafar, I. Valera, M. Gomez Rodriguez, K. P. Gummadi and A. Weller
NIPS 2017, Long Beach, CA, December 2017.
[PDF] [arXiv] [Code]
Also presented at FATML 2017, Halifax, Canada, August 2017. -
On Fairness, Diversity and Randomness in Algorithmic Decision Making
N. Grgić-Hlača, M. B. Zafar, K. P. Gummadi and A. Weller
FATML 2017, Halifax, Canada, August 2017.
[arXiv] -
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
M. B. Zafar, I. Valera, M. Gomez Rodriguez and K. P. Gummadi
WWW 2017, Perth, Australia, April 2017. (Best Paper Honorable Mention)
[PDF] [arXiv] [Code]
Also presented at FATML 2016, New York, NY, November 2016. -
Fairness Constraints: Mechanisms for Fair Classification
M. B. Zafar, I. Valera, M. Gomez Rodriguez and K. P. Gummadi
AISTATS 2017, Fort Lauderdale, FL, April 2017.
[PDF] [arXiv] [Code]
Also presented at FATML 2015, Lille, France, July 2015. -
Quantifying Search Bias: Investigating Sources of Bias for Political Searches in Social Media
J. Kulshrestha, M. Eslami, J. Messias, M. B. Zafar, S. Ghosh, K. P. Gummadi and K. Karahalios
CSCW 2017, Portland, OR, February 2017.
[PDF]
-
The Case for Temporal Transparency: Detecting Policy Change Events in Black-Box Decision Making Systems
M. Ferreira, M. B. Zafar and K. P. Gummadi
FATML 2016, New York, NY, November 2016.
[arXiv] -
Listening to Whispers of Ripple: Linking Wallets and Deanonymizing Transactions in the Ripple Network
P. Moreno-Sanchez, M. B. Zafar and A. Kate
PETS 2016, Darmstadt, Germany, May 2016.
[PDF] -
Message Impartiality in Social Media Discussions
M. B. Zafar, K. P. Gummadi and C. Danescu-Niculescu-Mizil
ICWSM 2016, Cologne, Germany, May 2016.
[PDF] [Data] -
On the Wisdom of Experts vs. Crowds: Discovering Trustworthy Topical News in Microblogs
M. B. Zafar, P. Bhattacharya, N. Ganguly, S. Ghosh and K. P. Gummadi
CSCW 2016, San Francisco, CA, February 2016.
[PDF]
-
Strength in Numbers: Robust Tamper Detection in Crowd Computations
B. Viswanath, M. A. Bashir, M. B. Zafar, S. Bouget, S Guha, K. P. Gummadi, A. Kate and A. Mislove
COSN 2015, Palo Alto, CA, October 2015. (Best Paper Award)
[PDF] -
Sampling Content from Online Social Networks: Comparing Random vs. Expert Sampling of the Twitter Stream
M. B. Zafar, P. Bhattacharya, N. Ganguly, K. P. Gummadi and S. Ghosh
ACM TWEB, June 2015.
[PDF] -
Characterizing Information Diets of Social Media Users
J. Kulshrestha, M. B. Zafar, L. E. Noboa, K. P. Gummadi and S. Ghosh
ICWSM 2015, Oxford, UK, May 2015.
[PDF]
-
Inferring User Interests in the Twitter Social Network
P. Bhattacharya, M. B. Zafar, N. Ganguly, S. Ghosh and K. P. Gummadi
RecSys 2014, Silicon Valley, CA, October 2014. (Short paper)
[PDF] -
Deep Twitter Diving: Exploring Topical Groups in Microblogs at Scale
P. Bhattacharya, S. Ghosh, J. Kulshrestha, M. Mondal, M. B. Zafar, N. Ganguly and K. P. Gummadi
CSCW 2014, Baltimore, MD, February 2014.
[PDF]
-
On Sampling the Wisdom of Crowds: Random vs. Expert Sampling of the Twitter Stream
S. Ghosh, M. B. Zafar, P. Bhattacharya, N. Sharma, N. Ganguly and K. P. Gummadi
CIKM 2013, Burlingame, CA, October 2013.
[PDF] -
SplitBuff: Improving the Interaction of Heterogeneous RTT Flows on the Internet
S. Jabeen, M. B. Zafar, I. A. Qazi and Z. A. Uzmi
ICC 2013, Budapest, Hungary, June 2013.
[PDF]
Education
- Max Planck Institute for Software Systems & Saarland University, Germany (2019)
PhD in Computer Science - Saarland University, Germany (2015)
MS in Computer Science - SBA School of Science and Engineering, LUMS, Pakistan (2012)
BS in Computer Science
Teaching
-
Human vs. Algorithmic Decision Making: Bias, Fairness and Transparency (Teaching Assistant)
Max Planck Institute for Software Systems & Saarland University, Winter Semester 2015-16. -
Database Systems (Teaching Assistant)
Saarland University, Summer Semester 2014. -
Advanced Programming (Teaching Assistant)
LUMS School of Science and Engineering, Spring Semester 2012.