SUJIT GUJAR
Currently, I am working as Assistant Professor at the International Institute of Information Technology, Hyderabad. Prior to this, I was a post-doctoral researcher with Prof Boi Faltings, LIA, EPFL, Lausanne (Jan'14-Oct'15), and a Sr Research Associate with Prof Y Narahari (Nov'15-Apr'16). I was a Research Scientist at Xerox Research Centre India (Jan'11-Nov'13). I completed my Ph.D. in the Department of Computer Science and Automation @ the Indian Institute of Science, Bangalore. I worked with Prof Y Narahari, Game Theory Lab. I am a recipient of the Alumni Medal of IISc for the Best Thesis in CSA for the academic year 2011-12' for my Ph.D. Dissertation, Novel Mechanisms for Allocation of Heterogeneous Items in Strategic Settings. During my Ph.D. I was a recipient of the Infosys Doctoral Fellowship.
Research Interests
Game Theory and Mechanism Design
Application of Game Theory to Artificial Intelligence (AI)
Social networks
Internet advertising
Crowdsourcing
Crowdfunding
Intelligent transportation
Online education
AI and Machine Learning
Cryptographic Game Theory (Securing Auctions)
Distributing trust: Block-chain Technology
Game Theory and Machine Learning
Recent Updates
Our paper "Welfare Optimal Combinatorial Civic Crowdfunding with Budgeted Agents" has been accepted at GAIW'22.
Our following paper "Tiramisu: Layering Consensus Protocols for Scalable and Secure Blockchains" got accepted at IEEE ICBC'22.
Our following papers got accepted in AAMAS 2022
Budgeted Combinatorial Multi-Armed Bandits
REFORM: Reputation Based Fair and Temporal Reward Framework for Crowdsourcing
Multi-unit Double Auctions: Equilibrium Analysis and Bidding Strategy using DDPG in Smart-grids
Our paper, "How Private Is Your RL Policy? An Inverse RL Based Analysis Framework" is accepted for publication at AAAI 2022
Openings
I have few openings for highly motivated Master and Ph.D. students to work on fascinating research problems in applied game theory as well as research challenges that lie at the intersection of Machine Learning and Game Theory and blockchain technology. I am excited about how to design protocols/ algorithms for modern marketplaces strategy-proof, that is, strategic agents do not manipulate it. I am also intrigued by the fact that with appropriate incentive engineering, blockchain technology has not just solved distributed consensus, but enabled to distribute the trust across the whole network. Through different research problems, my vision is to make AI and distributed systems fairer and strategyproof. Note you must be admitted to IIITH if you are interested in working with me as a regular student. If you are interested, you can drop an email to schedule a meeting. Currently, I do not have any internship openings for Bachelor's or Master's students.
Professional Activities
SPC Member: IJCAI 2021
PC member: UAI22, UAI 2021, IJCAI 2022, 2020, 2019, 2018,2017,2016. AAMAS 2020,2019,2018,2017. AAAI 2022, 2021, 2020. WINE 2017.
Reviewer: Conferences TheWebConf 2019, FSTCCS'15, ACM EC'15, AAAI'15, ICOR'12 WINE'12,
Journals JAIR, MACH, AI, GEB, EJOR, TMC, ECRA, IEEE SMC, JAAMAS
Teaching
CSE504: Fairness, Privacy and Ethics in AI
CSE201: Data Structures and Algorithms (Spring 2021,22) (IIITH)
CSE435: Advanced Communication Networks (Monsoon 2018,19,20) (IIITH)
CSE512: Distributing Trust and Blockchains (Spring 2018, Monsoon 2018,19,20,21) (IIITH)
CSE481: Optimization Methods (Spring 2017,18) (IIITH)
CSE498: Introduction to Game Theory (Monsoon 2016,17, Spring 2019,20,21,22) (IIITH)
Advanced Topics in Algorithmic Game Theory and Mechanism Design (Spring 2015) (EPFL)
Recent Publications
Budgeted Combinatorial Multi-Armed Bandits, AAMAS 22
REFORM: Reputation Based Fair and Temporal Reward Framework for Crowdsourcing, AAMAS 2022
Multi-unit Double Auctions: Equilibrium Analysis and Bidding Strategy using DDPG in Smart-grids, AAMAS 2022
How Private Is Your RL Policy? An Inverse RL Based Analysis Framework, AAAI 2022
Blockchain-based Practical Multi-agent Secure Comparison and its Application in Auctions, Wi-IAT 2021
Mechanism Design without Money for Fair Allocations, Wi-IAT 2021
Learning Equilibrium Contributions in Multi-project Civic Crowdfunding, Wi-IAT 2021
Differentially Private Multi-Agent Constraint Optimization, Wi-IAT 2021
Fair Federated Learning for Heterogeneous Data, YRS CODS-COMAD 2022
PUPoW: A Framework for Designing Blockchains With Practically-Useful-Proof-Of-Work & VanityCoin, IEEE Blockchain 2021
Effect of Input Noise Dimension in GANs, ICONIP 2021
Federated Learning Meets Fairness and Differential Privacy, ICONIP 2021
Towards Mobile Distributed Ledger, IEEE IoT
Designing Bounded Min-knapsack Bandits Algorithm for Sustainable Demand Response, PRICAI 2021 and Spotlight Presentation at Tackling Climate Change with Machine Learning workshop at ICML 2021
Designing Refund Bonus Schemes for Provision Point Mechanism in Civic Crowdfunding, PRICAI 2021
Building Ethical AI: Federated Learning Meets Fairness and Differential Privacy, DAI 2021. Best Paper Award.
Ballooning Multi-Armed Bandits, AI Journal 2021
FASTEN: Fair and Secure Distributed Voting Using Smart Contracts, IEEE ICBC 2021
A Multi-Arm Bandit Approach To Subset Selection Under Constraints, AAMAS 2021
We might walk together, but I run faster: Network Fairness and Scalability in Blockchains, AAMAS 2021 (Best Poster Design)
Elsewhere
Vistor Count (Since 11 April 2007)