2022
|
| 103. | Kritika Prakash; Fiza Hussain; Praveen Paruchuri; Sujit Gujar How Private Is Your RL Policy? An Inverse RL Based Analysis Framework Conference Forthcoming 36th AAAI Conference on Artificial Intelligence , AAAI, Forthcoming. BibTeX @inproceedings{Kritika22,
title = {How Private Is Your RL Policy? An Inverse RL Based Analysis Framework},
author = {Kritika Prakash and Fiza Hussain and Praveen Paruchuri and Sujit Gujar},
year = {2022},
date = {2022-02-22},
booktitle = {36th AAAI Conference on Artificial Intelligence },
publisher = {AAAI},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
|
| 102. | Samhita Kanaparthy; Manisha Padala; Sankarshan Damle; Sujit Gujar Fair Federated Learning for Heterogeneous Data Conference Forthcoming Young Researchers Symposium, CODS-COMAD’22., Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 101. | Ashutosh Ranjan; Vinay Ramani; Sujit Gujar Dynamic Matching in Campus Placements: The Benefits and Affordability of the Dream Option Journal Article Forthcoming IMB Management Review, Forthcoming. BibTeX @article{Ashutosh22,
title = {Dynamic Matching in Campus Placements: The Benefits and Affordability of the Dream Option},
author = {Ashutosh Ranjan and Vinay Ramani and Sujit Gujar},
year = {2022},
date = {2022-01-01},
journal = {IMB Management Review},
keywords = {},
pubstate = {forthcoming},
tppubtype = {article}
}
|
2021
|
| 100. | Sankarshan Damle; Aleksei Triastcyn; Boi Faltings; Sujit Gujar Differentially Private Multi-Agent Constraint Optimization Conference Forthcoming To Appear in the Proceeding of The 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT ’21), Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 99. | Sankarshan Damle; Boi Faltings; Sujit Gujar Blockchain-based Practical Multi-agent Secure Comparison and its Application in Auctions Conference Forthcoming To Appear in the Proceeding of The 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT ’21), Forthcoming. BibTeX @inproceedings{Damle2021d,
title = {Blockchain-based Practical Multi-agent Secure Comparison and its Application in Auctions},
author = {Sankarshan Damle 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 = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
|
| 98. | Manisha Padala; Sankarshan Damle; Sujit Gujar Learning Equilibrium Contributions in Multi-project Civic Crowdfunding Conference Forthcoming To Appear in the Proceeding of The 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT ’21), Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 97. | Manisha Padala; Sujit Gujar Mechanism Design without Money for Fair Allocations Conference Forthcoming To Appear in the proceedings of the 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology 2021 (WI-IAT ’21)., Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 96. | Manisha Padala; Debojit Das; Sujit Gujar Effect of Input Noise Dimension in GANs Conference Forthcoming Proceedings 28th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific Neural Network Society 2021 (ICONIP ’21), Forthcoming. BibTeX @inproceedings{Padala2021,
title = {Effect of Input Noise Dimension in GANs},
author = {Manisha Padala and Debojit Das and Sujit Gujar
},
year = {2021},
date = {2021-12-08},
booktitle = {Proceedings 28th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific Neural Network Society 2021 (ICONIP ’21)},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
|
| 95. | Manisha Padala; Sankarshan Damle ; Sujit Gujar Federated Learning Meets Fairness and Differential Privacy Conference Forthcoming Proceedings of the 28th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific Neural Network Society 2021 (ICONIP ’21), Forthcoming. BibTeX @inproceedings{Manisha2021b,
title = {Federated Learning Meets Fairness and Differential Privacy},
author = {Manisha Padala and Sankarshan Damle, and Sujit Gujar},
year = {2021},
date = {2021-12-08},
publisher = {Proceedings of the 28th International Conference on Neural Information Processing (ICONIP) of the Asia-Pacific Neural Network Society 2021 (ICONIP ’21)},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
|
| 94. | Gaurav Batra; Naresh Manwani Multiclass Classification using Dilute Bandit Feedback Conference Forthcoming PRICAI 2021, Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 93. | Meghana Reddy; Akansha Singh; Shweta Jain; Sujit Gujar Designing Bounded Min-knapsack Bandits Algorithm for Sustainable Demand Response Conference Forthcoming 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2021) , Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 92. | Sankarshan Damle; Moin Hussain Moti; Praphul Chandra; Sujit Gujar Designing Refund Bonus Schemes for Provision Point Mechanism in Civic Crowdfunding Conference Forthcoming 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI-2021) , Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 91. | Sarath Sivaprasad; Ankur Singh; Naresh Manwani; Vineet Gandhi The Curious Case of Convex Networks Conference Forthcoming ECML 2021, Forthcoming. BibTeX @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}
}
|
| 90. | Bhavya Kalra; Naresh Manwani RISAN: Robust Instance Specific Deep Abstention Network Conference Forthcoming UAI 2021, Forthcoming. BibTeX @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}
}
|
| 89. | Jaikumar Radhakrishnan Girish Varma Prerona Chatterjee Kshitij Gajjar Generalized Parametric Path Problems Conference Forthcoming 37th Conference on Uncertainty in Artificial Intelligence (UAI) 2021, Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 88. | Meghana Reddy; Akansha Singh; Zoltan Nagy; Sujit Gujar; Shweta Jain Designing Bounded min-Knapsack Bandits Algorithm for Sustainable Demand Response Workshop Tackling Climate Change with Machine Learning, ICML , 2021. BibTeX @workshop{MReddy2021a,
title = {Designing Bounded min-Knapsack Bandits Algorithm for Sustainable Demand Response},
author = {Meghana Reddy and Akansha Singh and Zoltan Nagy and Sujit Gujar and Shweta Jain},
year = {2021},
date = {2021-07-23},
booktitle = {Tackling Climate Change with Machine Learning, ICML },
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 87. | Padala Manisha; Sankarshan Damle; Sujit Gujar Building Ethical AI: Federated Learning meets Fairness and Privacy Conference First Indian Conference on Deployable AI, 2021. BibTeX @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 = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 86. | Mudit Agarwal; Naresh Manwani Learning Multiclass Classifier Under Noisy Bandit Feedback Conference Forthcoming PAKDD 2021, Forthcoming. BibTeX @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 = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 85. | Bhavya Kalra; Sai Krishna Munnangi; Kushal Majmundar; Naresh Manwani; Praveen Paruchuri Cooperative Monitoring of Malicious Activity in Stock Exchanges Workshop Workshop on Data Assessment and Readiness for Artificial Intelligence, PAKDD 2021, 2021. BibTeX @workshop{Bhavya-et.-al-2021,
title = {Cooperative Monitoring of Malicious Activity in Stock Exchanges},
author = {Bhavya Kalra and Sai Krishna Munnangi and Kushal Majmundar and Naresh Manwani and Praveen Paruchuri},
year = {2021},
date = {2021-05-15},
booktitle = {Workshop on Data Assessment and Readiness for Artificial Intelligence, PAKDD 2021},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 84. | Anurag Jain; Shoeb Siddiqui; Sujit Gujar We might walk together, but I run faster: Network Fairness and Scalability in Blockchains Conference Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), 2021. Abstract | BibTeX @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 = {},
pubstate = {published},
tppubtype = {conference}
}
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. |
| 83. | Ayush Deva; Kumar Abhishek; Sujit Gujar A Multi-Arm Bandit Approach To Subset Selection Under Constraints Conference International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021, 2021. BibTeX @conference{deva21,
title = {A Multi-Arm Bandit Approach To Subset Selection Under Constraints},
author = {Ayush Deva and Kumar Abhishek and Sujit Gujar},
year = {2021},
date = {2021-05-05},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2021},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 82. | Sankarshan Damle; Sujit Gujar; Moin Hussain Moti FASTEN: Fair and Secure Distributed Voting Using Smart Contracts Conference IEEE International Conference on Blockchain and Cryptocurrency (IEEE ICBC 2021), 2021. BibTeX @inproceedings{Damle2021,
title = {FASTEN: Fair and Secure Distributed Voting Using Smart Contracts},
author = {Sankarshan Damle and Sujit Gujar and Moin Hussain Moti},
year = {2021},
date = {2021-05-04},
booktitle = {IEEE International Conference on Blockchain and Cryptocurrency (IEEE ICBC 2021)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 81. | Ayush Deva; Kumar Abhishek; Sujit Gujar A Multi-Arm Bandit Approach To Subset Selection Under Constraints Workshop ALA 2021, Adaptive and Learning Agents Workshop at AAMAS 2021, 2021. BibTeX @workshop{Deva2021,
title = {A Multi-Arm Bandit Approach To Subset Selection Under Constraints},
author = {Ayush Deva and Kumar Abhishek and Sujit Gujar},
year = {2021},
date = {2021-05-03},
booktitle = {ALA 2021, Adaptive and Learning Agents Workshop at AAMAS 2021},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 80. | Ganesh Ghalme; Swapnil Dhamal; Shweta Jain; Sujit Gujar; Narahari Y Ballooning Multi-armed Bandits Journal Article Forthcoming Journal of Artificial Intelligence, Forthcoming. BibTeX @article{Ghalme21a,
title = {Ballooning Multi-armed Bandits},
author = {Ganesh Ghalme and Swapnil Dhamal and Shweta Jain and Sujit Gujar and Y Narahari},
year = {2021},
date = {2021-04-05},
journal = {Journal of Artificial Intelligence},
keywords = {},
pubstate = {forthcoming},
tppubtype = {article}
}
|
| 79. | Sankarshan Damle; Aleksei Triastcyn; Boi Faltings; Sujit Gujar Differentially Private Multi-Agent Constraint Optimization Workshop The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21), 2021. Abstract | Links | BibTeX @workshop{Damle2021b,
title = {Differentially Private Multi-Agent Constraint Optimization},
author = {Sankarshan Damle and Aleksei Triastcyn and Boi Faltings and Sujit Gujar},
editor = {Ferdinando Fioretto},
url = {https://ppai21.github.io/files/38-paper.pdf},
year = {2021},
date = {2021-02-08},
booktitle = {The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21)},
abstract = {Several optimization scenarios involve multiple agents that
desire to protect the privacy of their preferences. There ex-
ist distributed algorithms for constraint optimization that pro-
vide improved privacy protection through secure multiparty
computation. However, it comes at the expense of high com-
putational complexity and does not constitute a rigorous pri-
vacy guarantee, as the result of the computation itself may
compromise agents’ preferences. In this work, we show how
to achieve differential privacy through randomization of the
solving process. In particular, we present P-Gibbs, which
adapts the SD-Gibbs algorithm to obtain differential privacy
guarantees with much higher computational efficiency. Ex-
periments on graph coloring and meeting scheduling show
the algorithm’s privacy-performance trade-off compared to
variants with uniform sampling and the SD-Gibbs algorithm.},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
Several optimization scenarios involve multiple agents that
desire to protect the privacy of their preferences. There ex-
ist distributed algorithms for constraint optimization that pro-
vide improved privacy protection through secure multiparty
computation. However, it comes at the expense of high com-
putational complexity and does not constitute a rigorous pri-
vacy guarantee, as the result of the computation itself may
compromise agents’ preferences. In this work, we show how
to achieve differential privacy through randomization of the
solving process. In particular, we present P-Gibbs, which
adapts the SD-Gibbs algorithm to obtain differential privacy
guarantees with much higher computational efficiency. Ex-
periments on graph coloring and meeting scheduling show
the algorithm’s privacy-performance trade-off compared to
variants with uniform sampling and the SD-Gibbs algorithm. |
| 78. | Maanik Arora; Naresh Manwani Exact Passive Aggressive Algorithm for Multiclass Classification Using Partial Labels Conference Forthcoming CoDS-COMAD 2021, Forthcoming. BibTeX @conference{Maanik2021_CODS-COMAD,
title = {Exact Passive Aggressive Algorithm for Multiclass Classification Using Partial Labels},
author = {Maanik Arora and Naresh Manwani},
year = {2021},
date = {2021-01-10},
booktitle = {CoDS-COMAD 2021},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 77. | Daksh Anand; Vaibhav Gupta; Praveen Paruchuri; Balaraman Ravindran An Enhanced Advising Model in Teacher-Student Framework using State
Categorization Conference Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021, pp. 6653–6660, AAAI Press, 2021. Links | BibTeX @inproceedings{DBLP:conf/aaai/AnandGPR21,
title = {An Enhanced Advising Model in Teacher-Student Framework using State
Categorization},
author = {Daksh Anand and Vaibhav Gupta and Praveen Paruchuri and Balaraman Ravindran},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/16823},
year = {2021},
date = {2021-01-01},
booktitle = {Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9,
2021},
pages = {6653–6660},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 76. | Vaibhav Gupta; Daksh Anand; Praveen Paruchuri; Akshat Kumar Action Selection for Composable Modular Deep Reinforcement Learning Conference Dignum, Frank; Lomuscio, Alessio; Endriss, Ulle; é, Ann Now (Ed.): AAMAS ’21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021, pp. 565–573, ACM, 2021. Links | BibTeX @inproceedings{DBLP:conf/atal/GuptaAPK21,
title = {Action Selection for Composable Modular Deep Reinforcement Learning},
author = {Vaibhav Gupta and Daksh Anand and Praveen Paruchuri and Akshat Kumar},
editor = {Frank Dignum and Alessio Lomuscio and Ulle Endriss and Ann Now \'{e}},
url = {https://dl.acm.org/doi/10.5555/3463952.3464022},
year = {2021},
date = {2021-01-01},
booktitle = {AAMAS ’21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {565–573},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 75. | Dimitris Chatzopoulos; Anurag Jain; Sujit Gujar; Boi Faltings; Pan Hui Towards Mobile Distributed Ledgers Journal Article IEEE Internet of Things Journal, 2021. BibTeX @article{chatzopoulos2021mobile,
title = {Towards Mobile Distributed Ledgers},
author = {Dimitris Chatzopoulos and Anurag Jain and Sujit Gujar and Boi Faltings and Pan Hui},
year = {2021},
date = {2021-01-01},
journal = {IEEE Internet of Things Journal},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2020
|
| 74. | Sanidhay Arora; Anurag Jain; Sankarshan Damle; Sujit Gujar ASHWAChain: A Fast, Scalable and Strategy-proof Committee-based Blockchain Protocol Workshop Workshop on Game Theory in Blockchain at WINE 2020 (GTiB@WINE 2020), 2020. BibTeX @workshop{Arora2020,
title = {ASHWAChain: A Fast, Scalable and Strategy-proof Committee-based Blockchain Protocol},
author = {Sanidhay Arora and Anurag Jain and Sankarshan Damle and Sujit Gujar},
editor = {Jing Chen and Xiaotie Deng},
year = {2020},
date = {2020-12-11},
booktitle = {Workshop on Game Theory in Blockchain at WINE 2020 (GTiB@WINE 2020)},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 73. | Anurag Jain; Sujit Gujar Block Rewards, Not Transaction Fees Keep Miners Faithful In Blockchain Protocols Workshop Workshop on Game Theory in Blockchain at WINE 2020 (GTiB@WINE 2020), 2020. BibTeX @workshop{Jain2020,
title = {Block Rewards, Not Transaction Fees Keep Miners Faithful In Blockchain Protocols},
author = {Anurag Jain and Sujit Gujar },
editor = {Jing Chen and Xiaotie Deng},
year = {2020},
date = {2020-12-11},
booktitle = {Workshop on Game Theory in Blockchain at WINE 2020 (GTiB@WINE 2020)},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 72. | Maanik Arora; Naresh Manwani Exact Passive Aggressive Algorithm for Multiclass Classification Using Bandit Feedbacks Conference ACML 2020, 2020. Links | BibTeX @conference{Maanik2020_ACML,
title = {Exact Passive Aggressive Algorithm for Multiclass Classification Using Bandit Feedbacks},
author = {Maanik Arora and Naresh Manwani},
url = {http://proceedings.mlr.press/v129/arora20a.html},
year = {2020},
date = {2020-11-30},
booktitle = {ACML 2020},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 71. | Bhanu Garg; Naresh Manwani Robust Deep Ordinal Regression under Label Noise Conference ACML 2020, 2020. Links | BibTeX @conference{Bhanu2020_ACML,
title = {Robust Deep Ordinal Regression under Label Noise},
author = {Bhanu Garg and Naresh Manwani},
url = {http://proceedings.mlr.press/v129/garg20a.html},
year = {2020},
date = {2020-11-30},
booktitle = {ACML 2020},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 70. | Padala Manisha; Sujit Gujar FNNC: Achieving Fairness through Neural Networks Conference The 29th International Joint Conference on Artificial Intelligence, IJCAI 2020, 2020. Abstract | BibTeX @conference{manisha2020a,
title = {FNNC: Achieving Fairness through Neural Networks},
author = {Padala Manisha and Sujit Gujar},
year = {2020},
date = {2020-07-11},
booktitle = {The 29th International Joint Conference on Artificial Intelligence, IJCAI 2020},
abstract = {The classification models ensure fairness by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
The classification models ensure fairness by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints. |
| 69. | Praveen Paruchuri; Sreeja Kamishetty; Soumya Vadlamannati System and method for controlling vehicular pollution concentration and providing maximum traffic flow throughput Patent 2020. BibTeX @patent{Paruchuri2020,
title = {System and method for controlling vehicular pollution concentration and providing maximum traffic flow throughput },
author = {Praveen Paruchuri and Sreeja Kamishetty and Soumya Vadlamannati},
year = {2020},
date = {2020-06-25},
keywords = {},
pubstate = {published},
tppubtype = {patent}
}
|
| 68. | Rajarshi Bhattacharjee; Naresh Manwani Online Algorithms for Multiclass Classification using Partial Labels Conference PAKDD 2020, 2020. Links | BibTeX @inproceedings{Rajarshi2020,
title = {Online Algorithms for Multiclass Classification using Partial Labels},
author = {Rajarshi Bhattacharjee and Naresh Manwani},
url = {https://arxiv.org/abs/1912.11367},
year = {2020},
date = {2020-05-14},
booktitle = {PAKDD 2020},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 67. | Shoeb Siddiqui; Sujit Gujar; Ganesh Vanahalli BitcoinF: Achieving Fairness For Bitcoin In Transaction Fee Only Model Conference International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2020, 2020. BibTeX @conference{shoeb20a,
title = {BitcoinF: Achieving Fairness For Bitcoin In Transaction Fee Only Model},
author = {Shoeb Siddiqui and Sujit Gujar and Ganesh Vanahalli},
year = {2020},
date = {2020-05-11},
booktitle = {International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2020},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 66. | Kumar Abhishek; Shweta Jain; Sujit Gujar Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions Conference International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020, 2020. BibTeX @conference{abhishesk20a,
title = {Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions},
author = {Kumar Abhishek and Shweta Jain and Sujit Gujar },
year = {2020},
date = {2020-05-11},
booktitle = {International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 65. | Ganesh Ghalme; Swapnil Dhamal; Shweta Jain; Sujit Gujar; Yadati Narahari Ballooning Multi-Armed Bandits Conference International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2020, 2020. BibTeX @conference{ghalme20a,
title = {Ballooning Multi-Armed Bandits},
author = {Ganesh Ghalme and Swapnil Dhamal and Shweta Jain and Sujit Gujar and Yadati Narahari},
year = {2020},
date = {2020-05-11},
booktitle = {International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2020},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
| 64. | Sankarshan Damle; Moin Hussain Moti; Praphul Chandra; Sujit Gujar Designing Refund Bonus Schemes for Provision Point Mechanism in Civic Crowdfunding Workshop Games, Agents, and Incentives Workshop (GAIW@AAMAS 2020), 2020. Links | BibTeX @workshop{Damle2020,
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},
editor = {Sankarshan Damle},
url = {http://www.agent-games-2020.preflib.org/wp-content/uploads/2020/05/GAIW2020_paper_9.pdf},
year = {2020},
date = {2020-05-11},
booktitle = {Games, Agents, and Incentives Workshop (GAIW@AAMAS 2020)},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 63. | Moin Hussain Moti; Dimitris Chatzopoulos; Pan Hui; Boi Faltings; Sujit Gujar Orthos: A Trustworthy AI Framework For Data Acquisition Workshop 8th International Workshop on Engineering Multi-Agent Systems (EMAS 2020), 2020. BibTeX @workshop{Moti2020,
title = {Orthos: A Trustworthy AI Framework For Data Acquisition},
author = {Moin Hussain Moti and Dimitris Chatzopoulos and Pan Hui and Boi Faltings and Sujit Gujar },
editor = {Moin Hussain Moti},
year = {2020},
date = {2020-05-11},
booktitle = {8th International Workshop on Engineering Multi-Agent Systems (EMAS 2020)},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 62. | Ganesh Ghalme; Swapnil Dhamal; Shweta Jain; Sujit Gujar; Narahari Y Ballooning Multi-Armed Bandits Workshop Adaptive and Learning Agents, 2020. BibTeX @workshop{Ghalme20b,
title = {Ballooning Multi-Armed Bandits},
author = {Ganesh Ghalme and Swapnil Dhamal and Shweta Jain and Sujit Gujar and Y Narahari},
year = {2020},
date = {2020-05-09},
booktitle = {Adaptive and Learning Agents},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
|
| 61. | Dimitris Chatzopoulos; Sujit Gujar; Boi Faltings; Pan Hui Mneme: A Mobile Distributed Ledger Conference IEEE Conference on Communication, INFOCOM, IEEE, 2020. BibTeX @inproceedings{dimhatzo20a,
title = {Mneme: A Mobile Distributed Ledger},
author = {Dimitris Chatzopoulos and Sujit Gujar and Boi Faltings and Pan Hui},
year = {2020},
date = {2020-04-27},
booktitle = {IEEE Conference on Communication, INFOCOM},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 60. | Naresh Manwani; Mohit Chandra Exact Passive Aggressive Learning of Ordinal Regression Using Interval Labels Journal Article IEEE Transactions on Neural Networks and Learning Systems (NNLS), 2020. Links | BibTeX @article{Naresh_NNLS2020,
title = {Exact Passive Aggressive Learning of Ordinal Regression Using Interval Labels},
author = {Naresh Manwani and Mohit Chandra},
url = {https://ieeexplore.ieee.org/document/8867949},
year = {2020},
date = {2020-02-29},
journal = {IEEE Transactions on Neural Networks and Learning Systems (NNLS)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
| 59. | Susobhan Ghosh; Sujit Gujar; Praveen Paruchuri; Easwar Subramanian; Sanjay P Bidding in Smart Grid PDAs: Theory, Analysis and Strategy Conference AAAI, AAAI Press, 2020. Links | BibTeX @inproceedings{ghosh20a,
title = {Bidding in Smart Grid PDAs: Theory, Analysis and Strategy},
author = {Susobhan Ghosh and Sujit Gujar and Praveen Paruchuri and Easwar Subramanian and Sanjay P},
url = {https://www.researchgate.net/publication/337337754_Bidding_in_Smart_Grid_PDAs_Theor},
year = {2020},
date = {2020-02-07},
booktitle = {AAAI},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 58. | Shweta Jain; Sujit Gujar A Multiarmed Bandit Based Incentive Mechanism for a Subset Selection of Customers for Demand Response in Smart Grids Conference AAAI, AAAI Press, 2020. BibTeX @inproceedings{sjain20a,
title = {A Multiarmed Bandit Based Incentive Mechanism for a Subset Selection of Customers for Demand Response in Smart Grids},
author = {Shweta Jain and Sujit Gujar},
year = {2020},
date = {2020-02-07},
booktitle = {AAAI},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
| 57. | Kulin Shah; Naresh Manwani Online Active Learning of Reject Option Classifiers Conference Forthcoming AAAI, AAAI Press, Forthcoming. Links | BibTeX @conference{Kulin2020,
title = {Online Active Learning of Reject Option Classifiers},
author = {Kulin Shah and Naresh Manwani},
url = {https://arxiv.org/abs/1906.06166},
year = {2020},
date = {2020-02-07},
booktitle = {AAAI},
publisher = {AAAI Press},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
|
| 56. | Himanshu Kumar; Naresh Manwani; Sastry P S Robust Learning of Multi-Label Classifiers under Label Noise Conference ACM India Joint International Conference on Data Science & Management of Data, 2020. Abstract | Links | BibTeX @conference{Himanshu_CoDS2020,
title = {Robust Learning of Multi-Label Classifiers under Label Noise},
author = {Himanshu Kumar and Naresh Manwani and P.S. Sastry},
doi = {https://doi.org/10.1145/3371158.3371169},
year = {2020},
date = {2020-01-07},
booktitle = {ACM India Joint International Conference on Data Science & Management of Data},
pages = {90-97},
abstract = {In this paper, we address the problem of robust learning of multi-label classifiers when the training data has label noise. We consider learning algorithms in the risk-minimization framework. We define what we call symmetric label noise in multi-label settings which is a useful noise model for many random errors in the labeling of data. We prove that risk minimization is robust to symmetric label noise if the loss function satisfies some conditions. We show that Hamming loss and a surrogate of Hamming loss satisfy these sufficient conditions and hence are robust. By learning feedforward neural networks on some benchmark multi-label datasets, we provide empirical evidence to illustrate our theoretical results on the robust learning of multi-label classifiers under label noise.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this paper, we address the problem of robust learning of multi-label classifiers when the training data has label noise. We consider learning algorithms in the risk-minimization framework. We define what we call symmetric label noise in multi-label settings which is a useful noise model for many random errors in the labeling of data. We prove that risk minimization is robust to symmetric label noise if the loss function satisfies some conditions. We show that Hamming loss and a surrogate of Hamming loss satisfy these sufficient conditions and hence are robust. By learning feedforward neural networks on some benchmark multi-label datasets, we provide empirical evidence to illustrate our theoretical results on the robust learning of multi-label classifiers under label noise. |
| 55. | Saurabh Ravindranath; Rahul Baburaj; Vineeth Balasubramanian; Nageswararao Namburu; Sujit Gujar; Jawahar C V Human-Machine Collaboration for Face Recognition Conference 7th ACM India Joint International Conference on
Data Science & Management of Data, COMAD/CODS, ACM, 2020. Abstract | Links | BibTeX @conference{Ravindranath20a,
title = {Human-Machine Collaboration for Face Recognition},
author = {Saurabh Ravindranath and Rahul Baburaj and Vineeth Balasubramanian and Nageswararao Namburu and Sujit Gujar and C V Jawahar},
doi = {https://doi.org/10.1145/3371158.3371160},
year = {2020},
date = {2020-01-05},
booktitle = {7th ACM India Joint International Conference on
Data Science & Management of Data, COMAD/CODS},
publisher = {ACM},
abstract = {Despite advances in deep learning and facial recognition techniques, the problem of fault-intolerant facial recognition remains challenging. With the current state of progress in the field of automatic face recognition and the in-feasibility of fully manual recognition, the situation calls for human-machine collaborative methods. We design a system that uses machine predictions for a given face to generate queries that are answered by human experts to provide the system with the information required to predict the identity of the face correctly. We use a Markov Decision Process for which we devise an appropriate query structure and a reward structure to generate these queries in a budget or accuracy-constrained setting. Finally, as we do not know the capabilities of the human experts involved, we model each human as a bandit and adopt a multi-armed bandit approach with consensus queries to efficiently estimate their individual accuracies , enabling us to maximize the accuracy of our system. Through careful analysis and experimentation on real-world data-sets using humans, we show that our system outperforms methods that exploit only machine intelligence, simultaneously being highly cost-efficient as compared to fully manual methods. In summary, our system uses human-machine collaboration for face recognition problem more intelligently and efficiently.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Despite advances in deep learning and facial recognition techniques, the problem of fault-intolerant facial recognition remains challenging. With the current state of progress in the field of automatic face recognition and the in-feasibility of fully manual recognition, the situation calls for human-machine collaborative methods. We design a system that uses machine predictions for a given face to generate queries that are answered by human experts to provide the system with the information required to predict the identity of the face correctly. We use a Markov Decision Process for which we devise an appropriate query structure and a reward structure to generate these queries in a budget or accuracy-constrained setting. Finally, as we do not know the capabilities of the human experts involved, we model each human as a bandit and adopt a multi-armed bandit approach with consensus queries to efficiently estimate their individual accuracies , enabling us to maximize the accuracy of our system. Through careful analysis and experimentation on real-world data-sets using humans, we show that our system outperforms methods that exploit only machine intelligence, simultaneously being highly cost-efficient as compared to fully manual methods. In summary, our system uses human-machine collaboration for face recognition problem more intelligently and efficiently. |
| 54. | Sreeja Kamishetty; Soumya Vadlamannati; Praveen Paruchuri Towards a better management of urban traffic pollution using a Pareto max flow approach Journal Article Transportation Research Part D: Transport and Environment, 79 , pp. 102194, 2020. BibTeX @article{kamishetty2020towards,
title = {Towards a better management of urban traffic pollution using a Pareto max flow approach},
author = {Sreeja Kamishetty and Soumya Vadlamannati and Praveen Paruchuri},
year = {2020},
date = {2020-01-01},
journal = {Transportation Research Part D: Transport and Environment},
volume = {79},
pages = {102194},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
