Department of Computer Science and Engineering

Indian Institute of Technology Hyderabad (IITH) is a premier institute of science and technology established in 2008. IITH has been consistently ranked in the&nbsp;<a href="https://iith.ac.in/reports/" rel="noopener noreferrer">top 10 institutes</a>&nbsp;in India for Engineering&nbsp;<a href="https://www.nirfindia.org/2021/EngineeringRanking.html" rel="noopener noreferrer" target="_blank">according to NIRF</a>&nbsp;making it one of the most coveted schools for science and technology in the country.

IITH offers&nbsp;<a href="https://iith.ac.in/academics/under-graduate/">undergraduate programs</a>&nbsp;in all the classical engineering disciplines, applied sciences, design, as well as several modern interdisciplinary areas. Students are given a flexibility to explore a broad set of areas, and potentially pursue a minor or double major in a discipline that is not their own. Students who wish to seek a deeper understanding of their own discipline are strongly encouraged to get involved in cutting-edge research with the help of a faculty to mentor them, and earn an Honors in their own field.

The very foundation of IIT Hyderabad is based on&nbsp;<a href="https://iith.ac.in/research/">research and innovation</a>. The vibrant research culture is evident from the number of patents and publications that IITH produces consistently every year. IITH offers&nbsp;<a href="https://iith.ac.in/academics/programmes-offered/">graduate programs</a>&nbsp;at both a masters, and a doctoral level, in several diverse areas. There are separate programs for technology, design, science, and liberal arts. The&nbsp;<a href="https://iith.ac.in/academics/post-graduate/">MTech program</a>&nbsp;is offered in various modes and durations to cater to the ever-growing need of postgraduate level professionals in the country.

IITH encourages and supports&nbsp;<a href="https://iic-iith.netlify.app/index.html" rel="noopener noreferrer" target="_blank">innovation and entrepreneurship</a>&nbsp;at every stage. The minor program in entrepreneurship is open to all students of IITH, and many of the courses are offered by industrialists who are entrepreneurs themselves. There are various&nbsp;<a href="https://iith.ac.in/research/centres-incubators/">innovation centers and incubators</a>&nbsp;that promote entrepreneurship and help mentor young innovators. IITH has been very successful in building tie-ups with leading academic institutions around the globe.

IITH enjoys a very special relationship with Japanese universities and industries that goes beyond academic and research collaborations. In fact, some of the iconic buildings in IITH campus will carry the signature of Japanese architecture.

IITH creates a unique holistic ecosystem for education that offers interactive learning, a very flexible academic structure, cutting-edge research, strong industry collaboration, and entrepreneurship. This is an environment which enables students and faculty to translate their dreams into realities.

IIT Hyderabad

Department of Artificial Intelligence

The state-of-the-art recourse generation methods solely rely on the user's profile (feature vector). However, two users having the same profile may still have different preferences. Consequently, the recourse generated from a single profile may not have the same appeal to both the users. For example, one rejected loan applicant may prefer changes in Savings Amount, whereas, another - being a financial expert - may prefer changes in Investment Amount. Taking into account these preferences in feature-change can be very helpful in generating more user-satisfying recourses. To this end, we propose a simple user-preference representation and design a method to generate a recourse that adheres to the user preference. We empirically demonstrate the effectiveness and ease of the proposed method at generating recourses satisfying user preferences. © 2023 Owner/Author.

World University root node

ACM International Conference Proceeding Series

Algorithmic Recourse based on User's Feature-order Preference

We revisit the problem of fair clustering, first introduced by Chierichetti et al. (Fair clustering through fairlets, 2017), which requires each protected attribute to have approximately equal representation in every cluster, i.e., a Balance property. Existing solutions to fair clustering are either not scalable or do not achieve an optimal trade-off between clustering objectives and fairness. In this paper, we propose a new notion of fairness which we call τ-ratio fairness, that strictly generalizes the Balance property and enables a fine-grained efficiency vs. fairness trade-off. Furthermore, we show that a simple greedy round-robin-based algorithm achieves this trade-off efficiently. Under a more general setting of multi-valued protected attributes, we rigorously analyze the theoretical properties of the proposed algorithm, the Fair Round-Robin Algorithm for Clustering Over-End (FRAC OE). We also propose a heuristic algorithm, Fair Round-Robin Algorithm for Clustering (FRAC), that applies round-robin allocation at each iteration of a vanilla clustering algorithm. Our experimental results suggest that both FRAC and FRAC OE outperform all the state-of-the-art algorithms and work exceptionally well even for a large number of clusters. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature.

Fulltext

Data Mining and Knowledge Discovery

Efficient algorithms for fair clustering with a new notion of fairness

Fairness has emerged as an important concern in automated decision-making in recent years, especially when these decisions affect human welfare. In this work, we study fairness in temporally extended decision-making settings, specifically those formulated as Markov Decision Processes (MDPs). Our proposed notion of fairness ensures that each state's long-term visitation frequency is at least a specified fraction. This quota-based notion of fairness is natural in many resource-allocation settings where the dynamics of a single resource being allocated is governed by an MDP and the distribution of the shared resource is captured by its state-visitation frequency. In an average-reward MDP (AMDP) setting, we formulate the problem as a bilinear saddle point program and, for a generative model, solve it using a Stochastic Mirror Descent (SMD) based algorithm. The proposed solution guarantees a simultaneous approximation on the expected average-reward and fairness requirement. We give sample complexity bounds for the proposed algorithm and validate our theoretical results with experiments on simulated data. © 2022 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved

Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment

Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused-strategic machines might craft representations that manipulate their users. How can a user make good choices based on strategic representations? We formalize this as a learning problem, and pursue algorithms for decision-making that are robust to manipulation. In our main setting of interest, the system represents attributes of an item to the user, who then decides whether or not to consume. We model this interaction through the lens of strategic classification (Hardt et al. 2016), reversed: the user, who learns, plays first; and the system, which responds, plays second. The system must respond with representations that reveal 'nothing but the truth' but need not reveal the entire truth. Thus, the user faces the problem of learning set functions under strategic subset selection, which presents distinct algorithmic and statistical challenges. Our main result is a learning algorithm that minimizes error despite strategic representations, and our theoretical analysis sheds light on the trade-off between learning effort and susceptibility to manipulation. Copyright © 2022 by the author(s)

Proceedings of Machine Learning Research

Strategic Representation

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as 'memory' for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a trained model is merely limited to either inference or better initialization towards a target task. In this paper, we go further and extract synthetic data by leveraging the learnt model parameters. We dub them Data Impressions, which act as proxy to the training data and can be used to realize a variety of tasks. These are useful in scenarios where only the pretrained models are available and the training data is not shared (e.g., due to privacy or sensitivity concerns). We show the applicability of data impressions in solving several computer vision tasks such as unsupervised domain adaptation, continual learning as well as knowledge distillation. We also study the adversarial robustness of lightweight models trained via knowledge distillation using these data impressions. Further, we demonstrate the efficacy of data impressions in generating data-free Universal Adversarial Perturbations (UAPs) with better fooling rates. Extensive experiments performed on benchmark datasets demonstrate competitive performance achieved using data impressions in absence of original training data. © 1979-2012 IEEE.

IEEE Transactions on Pattern Analysis and Machine Intelligence

Mining Data Impressions From Deep Models as Substitute for the Unavailable Training Data

Data augmentation has been a prevalent approach in improving the performance of deep learning models against slight variations in data. Adversarial learning is one such form of data augmentation. In this work, we aim to introduce a framework to generate harder examples for a specific object class and an adversarial attack for the object detection task. We have also presented our study on the effect of training against such generated harder examples and adversarial samples in object detection. We have applied this adversarial learning technique to a YOLOv3 model and due to the nature of the attack, we demonstrated a substantial improvement in average precision (AP) for a single class of the COCO dataset. As per the literature, we are the first to introduce this kind of class-specific data augmentation strategy in object detection. With our approach, we have shown an improvement of 23.34% in AP for Cat class and 3.1% on overall mAP of YOLOv3 model on clean validation data, while 43.5% improvement in AP for the Cat class on the composite images with class-specific adversarial samples. © 2022 IEEE.

Proceedings - International Conference on Pattern Recognition

Adv-Cut Paste: Semantic adversarial class specific data augmentation technique for object detection

The early detection of a stuck pipe event is crucial as it is one of the major incidents resulting in nonproductive time. An ordinary supervised machine learning approach has been adopted to achieve the detection of stuck pipe in some previous studies. However, for early detection before stuck occurs with this approach, there are challenging issues such as limited stuck pipe data, various causes of stuck, and the lack of a prior exact "stuck sign" which should be a label in the training dataset. In this study, the surface drilling data is first collected from multiple agencies to enhance the training dataset. Subsequently, a supervised machine learning algorithm with ordinary binary classification methodologies, such as support vector machines and neural networks is adopted. The supervised machine learning approach presents good performance for stuck pipe event detection. However, it detects "stuck has already occurred", and it cannot effectively predict the stuck pipe because there is no exact sign for stuck pipe which is mandatory as label for training data. This study also adopts an unsupervised machine learning algorithm which employs architectures that include an autoencoder with long short-term memory, as well as a multiple prediction model to improve the expressiveness. The unsupervised machine learning process typically involves learning the features of normal activities, whereby the created model can represent only these activities. When stuck occurs or will occur, as such data are not represented by the created model, it should be detected. The performance of the early stuck pipe event detection using supervised and unsupervised machine learning approaches is analyzed, and the results demonstrate that the unsupervised machine learning approach presents a better early stuck pipe detection capability. The proposed machine learning algorithm will be further improved in the future and the prediction result will be validated through actual operation. Copyright © 2022, Offshore Technology Conference.

Offshore Technology Conference Asia, OTCA 2022

Early Stuck Detection Using Supervised and Unsupervised Machine Learning Approaches

We study fairness in the context of feature-based price discrimination in monopoly markets. We propose a new notion of individual fairness, namely, α-fairness, which guarantees that individuals with similar features face similar prices. First, we study discrete valuation space and give an analytical solution for optimal fair feature-based pricing. We show that the cost of fair pricing is defined as the ratio of expected revenue in optimal feature-based pricing to the expected revenue in an optimal fair feature-based pricing (COF) can be arbitrarily large in general. When the revenue function is continuous and concave with respect to the prices, we show that one can achieve COF strictly less than 2, irrespective of the model parameters. Finally, we provide an algorithm to compute fair feature-based pricing strategy that achieves this COF. © 2022 UAI. All Rights Reserved.

Individual Fairness in Feature-Based Pricing for Monopoly Markets

In this paper we present a novel approach for detecting early signs for the stuck events in drilling using Deep Learning. Specifically, we adapt neural network based unsupervised learning tool called Autoencoder for anticipating the ‘stuck’ events during the drilling process. We build Autoencoders on Recurrent Neural Networks (RNNs) to model the normal drilling activity, thereby detecting the stuck incidents as anomalous activity. We conduct experiments on the actual drilling data collected from 30 field wells operated by multiple drilling sources with diverse well profiles and demonstrate that our approach obtains promising results for the stuck sign detection. Furthermore towards explaining the trained model's prediction, we present reconstruction analysis on the individual drilling parameters. © 2021 Elsevier B.V.

Journal of Petroleum Science and Engineering

Early sign detection for the stuck pipe scenarios using unsupervised deep learning

We study fairness in the context of feature-based price discrimination in monopoly markets. We propose a new notion of individual fairness, namely, α-fairness, which guarantees that individuals with similar features face similar prices. First, we study discrete valuation space and give an analytical solution for optimal fair feature-based pricing. We show that the cost of fair pricing is defined as the ratio of expected revenue in optimal feature-based pricing to the expected revenue in an optimal fair feature-based pricing (COF) can be arbitrarily large in general. When the revenue function is continuous and concave with respect to the prices, we show that one can achieve COF strictly less than 2, irrespective of the model parameters. Finally, we provide an algorithm to compute fair feature-based pricing strategy that achieves this COF. © 2022 Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022. All right reserved.