Search Publications

@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 = {fairness, Neural Networks},
pubstate = {forthcoming},
tppubtype = {conference}
}

@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 = {bitcoin, fairness},
pubstate = {forthcoming},
tppubtype = {conference}
}

@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 = {auctions, online learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@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 = {ActiveLearning, MAB, online learning},
pubstate = {forthcoming},
tppubtype = {conference}
}

@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 = {ActiveLearning, Online, RejectOption},
pubstate = {forthcoming},
tppubtype = {conference}
}

@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 = {Label Noise, Multi-Label, Robust},
pubstate = {published},
tppubtype = {conference}
}

@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 = {ActiveLearning, Face recognition, MAB},
pubstate = {published},
tppubtype = {conference}
}