Shahin Jabbari

Office: 3675 Market St, Office 1151, Philadelphia, PA, 19104
Email: shahin@drexel.edu
Phone: 215-895-2474

I am an assistant professor in the Computer Science Department of the College of Computing & Informatics at Drexel University where I am part of the EconCS group. From 2013 to 2019, I was a PhD student in the Computer and Information Science Department at University of Pennsylvania where I was fortunate to be advised by Michael Kearns. For the following two years, I was a CRCS postdoctoral fellow in the Computer Science Department of the School of Engineering and Applied Sciences at Harvard. I was lucky to be hosted by Milind Tambe and was also affiliated with the EconCS group.


Research Interests

My main interests are in machine learning, game theory and their intersection. These days, I mostly focus on the ethical aspects of algorithmic decision making and think about how AI driven technology can lead to positive societal impact.
If you are ineterested in working on any of these topics with me, please apply to our PhD program and mention me in your application.


Publications

Unless specified otherwise, authors are listed in alphabetical order.

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective

S. Krishna, T. Han, A. Gu, J. Pombra, S.J., S. Wu, H. Lakkaraju (contributional order)
Preprint 2022

A Game-Theoretic Approach for Hierarchical Epidemic Control

F. Jia, A. Mate, Z. Li, S.J., M. Chakraborty, M. Tambe, M. Wellman and Y. Vorobeychik (contributional order)
Preprint 2022

Solving Structured Hierarchical Games Using Differential Backward Induction

Z. Li, F. Jia, A. Mate, S.J., M. Chakraborty, M. Tambe and Y. Vorobeychik (contributional order)
UAI 2022 (Oral Presentation)

Combining Machine Learning and Cognitive Models for Adaptive Phishing Training

E. Cranford, S.J., H-C. Ou, M. Tambe, C. Gonzalez and C. Lebiere (contributional order)
ICCM 2022

Designing Effective Masking Strategies for Cyberdefense through Human Experimentation and Cognitive Models

P. Aggarwal, O. Thakoor, S.J., E. Cranford, C. Lebiere, M. Tambe and C. Gonzalez (contributional order)
Computers & Security 2022

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

S. Aggarwal, S.J., C. Agarwal, S. Upadhyay, Z.S. Wu and H. Lakkaraju (contributional order)
ICML 2021

Active Screening for Recurrent Diseases: A Reinforcement Learning Approach

H-C. Ou, H. Chen, S.J. and M. Tambe (contributional order)
AAMAS 2021 (Best Paper Finalist)

Fair Influence Maximization: A Welfare Optimization Approach

A. Rahmattalabi*, S.J.*, H. Lakkaraju, P. Vayanos, M. Izenberg, R. Brown, E. Rice and M. Tambe (contributional order, * equal contribution)
AAAI 2021

Modeling Between-Population Variation in COVID-19 Dynamics in Hubei, Lombardy, and New York City

B. Wilder, M. Charpignon, J. Killian, H-C. Ou, A. Mate, S.J., A. Perrault, A. Desai, M. Tambe and M. Majumder (contributional order)
PNAS 2020

Risk-based Cyber Camouflage Games and Exploiting Bounded Rationality

O. Thakoor, S.J., P. Aggarwal, C. Gonzalez, M. Tambe and P. Vayanos (contributional order)
GameSec 2020 (Best Paper)

Network Formation under Random Attack and Probabilistic Spread

with Y. Chen, M. Kearns, S. Khanna and J. Morgenstern
IJCAI 2019

Equilibrium Characterization for Data Acquisition Games

with J. Dong, H. Elzayn, M. Kearns and Z. Schutzman
IJCAI 2019

Fair Algorithms for Learning in Allocation Problems

with H. Elzayn, C. Jung, M. Kearns, S. Neel, A. Roth and Z. Schutzman
ACM FAT* 2019

Fairness in Criminal Justice Risk Assessments: The State of the Art

with R. Berk, H. Heidari, M. Kearns and A. Roth
Sociological Methods & Research 2018

A Convex Framework for Fair Regression

with R. Berk, H. Heidari, M. Joseph, M. Kearns, J. Morgenstern, S. Neel and A. Roth
FATML 2017

Fairness in Reinforcement Learning

with M. Joseph, M. Kearns, J. Morgenstern and A. Roth
ICML 2017

Strategic Network Formation with Attack and Immunization

with S. Goyal, M. Kearns, S. Khanna and J. Morgenstern
WINE 2016
ICML 2013

PAC-Learning with General Class Noise Models

S.J., R. Holte and S. Zilles (contributional order)
KI 2012 (Best Paper)

Teaching

CS T680: Responsible Machine Learning

Winter 2022

CS 465: Privacy

Spring 2022, Spring 2023

CS 590: Privacy

Fall 2022

Service

Junior Program Committee

AAAI 2019, FAccT 2022, EC 2020, 2021, WINE 2021

Reviewer

ICLR 2023, ICML 2020, 2021, 2022, NeurIPS 2014, 2015, 2018 (Top Reviewer!), 2019, 2020, 2021, 2022

External Reviewer

EC 2018, 2019, NeurIPS 2013, SAGT 2017, SODA 2022, WINE 2019

Journal Reviewer

AIJ 2020, PNAS Nexus 2022, TEAC 2021, TMLR 2022