Search Publications

@conference{Samhita22a,
title = {Fair Federated Learning for Heterogeneous Data},
author = {Samhita Kanaparthy and Manisha Padala and Sankarshan Damle and Sujit Gujar},
year = {2022},
date = {2022-01-05},
booktitle = {Young Researchers Symposium, CODS-COMAD'22.},
keywords = {fairness, federated learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Damle2021c,
title = {Differentially Private Multi-Agent Constraint Optimization},
author = {Sankarshan Damle and Aleksei Triastcyn and Boi Faltings and Sujit Gujar},
year = {2021},
date = {2021-12-14},
booktitle = {To Appear in the Proceeding of The 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT '21)},
keywords = {differential privacy, distributed constrained optimization},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Padala2021b,
title = {Learning Equilibrium Contributions in Multi-project Civic Crowdfunding},
author = {Manisha Padala and Sankarshan Damle and Sujit Gujar},
year = {2021},
date = {2021-12-14},
booktitle = {To Appear in the Proceeding of The 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT '21)},
keywords = {Civic Crowdfunding, Mechanism Design, Reinforcement Learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Padala2021c,
title = {Mechanism Design without Money for Fair Allocations},
author = {Manisha Padala and Sujit Gujar},
year = {2021},
date = {2021-12-14},
booktitle = {To Appear in the proceedings of the 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology 2021 (WI-IAT '21).},
keywords = {fairness, Mechanism Design},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Gaurav2021,
title = {Multiclass Classification using Dilute Bandit Feedback},
author = {Gaurav Batra and Naresh Manwani},
year = {2021},
date = {2021-11-12},
booktitle = {PRICAI 2021},
keywords = {Bandit Feedback, multiclass classification, online learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{MReddy2021b,
title = {Designing Bounded Min-knapsack Bandits Algorithm for Sustainable Demand Response},
author = {Meghana Reddy and Akansha Singh and Shweta Jain and Sujit Gujar},
year = {2021},
date = {2021-11-08},
booktitle = {18th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2021) },
keywords = {Multi-arm Bandits, smart grids},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{sankarshan2021b,
title = {Designing Refund Bonus Schemes for Provision Point Mechanism in Civic Crowdfunding},
author = {Sankarshan Damle and Moin Hussain Moti and Praphul Chandra and Sujit Gujar},
year = {2021},
date = {2021-11-08},
booktitle = {18th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2021) },
keywords = {Blockchains, Civic Crowdfunding, differential privacy, fairness, federated learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Sarath-et-al-2021,
title = {The Curious Case of Convex Networks},
author = {Sarath Sivaprasad and Ankur Singh and Naresh Manwani and Vineet Gandhi},
year = {2021},
date = {2021-09-17},
booktitle = {ECML 2021},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Bhavya-Naresh2021,
title = {RISAN: Robust Instance Specific Deep Abstention Network},
author = {Bhavya Kalra and Naresh Manwani},
year = {2021},
date = {2021-07-29},
booktitle = {UAI 2021},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Chatterjee2021,
title = {Generalized Parametric Path Problems},
author = {Prerona Chatterjee, Kshitij Gajjar, Jaikumar Radhakrishnan, Girish Varma},
year = {2021},
date = {2021-07-27},
booktitle = {37th Conference on Uncertainty in Artificial Intelligence (UAI) 2021},
journal = {Proceedings of Machine Learning Research},
keywords = {Artificial Intelligence},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{manisha2021a,
title = {Building Ethical AI: Federated Learning meets Fairness and Privacy},
author = {Padala Manisha and Sankarshan Damle and Sujit Gujar },
year = {2021},
date = {2021-06-17},
booktitle = {First Indian Conference on Deployable AI},
keywords = {differential privacy, fairness, federated learning},
pubstate = {published},
tppubtype = {conference}
}

@conference{Mudit2021,
title = {Learning Multiclass Classifier Under Noisy Bandit Feedback},
author = {Mudit Agarwal and Naresh Manwani},
year = {2021},
date = {2021-05-15},
booktitle = {PAKDD 2021},
keywords = {Bandit Feedback, Label Noise, multiclass classification, online learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@conference{Jain2021,
title = {We might walk together, but I run faster: Network Fairness and Scalability in Blockchains},
author = {Anurag Jain and Shoeb Siddiqui and Sujit Gujar},
editor = {U. Endriss and A. Now\'{e} and F. Dignum and A. Lomuscio },
year = {2021},
date = {2021-05-05},
booktitle = {Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)},
abstract = {Blockchain-based Distributed Ledgers (DLs) promise to transform the existing financial system by making it truly democratic. In the past decade, blockchain technology has seen many novel applications ranging from the banking industry to real estate. However, in order to be adopted universally, blockchain systems must be scalable to support a high volume of transactions. As we increase the throughput of the DL system, the underlying peer-to-peer network might face multiple levels of challenges to keep up with the requirements. Due to varying network capacities, the slower nodes would be at a relative disadvantage compared to the faster ones, which could negatively impact their revenue. In order to quantify their relative advantage or disadvantage, we introduce two measures of network fairness, p_f, the probability of frontrunning and alpha_f, the publishing fairness. We show that as we scale the blockchain, both these measures deteriorate, implying that the slower nodes face a disadvantage at higher throughputs. It results in the faster nodes getting more than their fair share of the reward while the slower nodes (slow in terms of network quality) get less. Thus, fairness and scalability in blockchain systems do not go hand in hand.
In a setting with rational miners, lack of fairness causes miners to deviate from the ``longest chain rule'' or emph{undercut}, which would reduce the blockchain's resilience against byzantine adversaries. Hence, fairness is not only a desirable property for a blockchain system but also essential for the security of the blockchain and any scalable blockchain protocol proposed must ensure fairness.},
keywords = {Blockchains, Distributed Ledgers, fairness, Peer-to-Peer Networks, Scalability},
pubstate = {published},
tppubtype = {conference}
}