Department of Data Science

Indian Institute of Technology Palakkad&nbsp;(IIT Palakkad or IIT PKD) is a public autonomous&nbsp;engineering&nbsp;and&nbsp;research&nbsp;institute located in&nbsp;Palakkad,&nbsp;Kerala. It was&nbsp;one of the five new&nbsp;IITs&nbsp;proposed in the&nbsp;2014 Union budget of India. The campus was inaugurated on 3 August 2015. The institute has 94 faculty, 978 students, and 63 non-teaching staffs.

IT Palakkad currently offers four-year Bachelor of Technology (B.Tech) and two years MS programmes in 8 different engineering disciplines including&nbsp;Computer Science, Electrical, Mechanical, Civil among others.

&nbsp;

IIT Palakkad

Traditional clustering often results in imbalanced clusters, limiting its suitability for real-world problems. In response, capacitated clustering methods have emerged, aiming to achieve balanced clusters by limiting points in each cluster. In this paper, we introduce online algorithms with provable bounds on opened centers and cost approximation. We validate our methods experimentally. © 2024 Owner/Author.

World University root node

ACM International Conference Proceeding Series

Online Algorithm for Clustering with Capacity Constraints

To better understand how accurate opaque black box models work, it is necessary to explain their internal workings in terms of human-interpretable image sub-regions known as concepts. This explanation will provide insights into how these models perceive the sharedness of concepts across related classes, as frequently observed in the real world. With this objective in mind, the proposed work aims to leverage an incremental Non-negative Matrix Factorization technique to extract shared concepts in a memory-efficient manner, thereby reflecting the sharedness of concepts across classes. The relevance of the extracted concepts towards prediction, as well as the encoding of primitive image aspects such as color, texture and shape by the concept, will be estimated after training the concept extractor. This approach reduces training overhead and simplifies the explanation pipeline, enabling the elucidation of various concepts - some genuine, some spurious - on which different black box architectures trained on the Imagenet dataset group and distinguish related classes. © 2024 ACM.

SCE: Shared Concept Extractor to Explain a CNN's Classification Dynamics

Fuel cells are the efficient electrochemical energy conversion devices with wide-ranging applications. Polymer Electrolyte Membrane (PEM) is the primary component of a PEM fuel cell whose proton conductivity majorly determines the performance of the fuel cells. Due to the high cost and limited range of operating parameters, alternatives of perfluorinated ionomers based commercial PEMs are urgently required. Sulfonated polyimides (SPIs) based hydrocarbon PEMs, have exhibited better proton conductivity even at low hydration levels and high temperatures, making them possible candidates for replacing commercial PEMs. However, finding alternative SPI PEMs is a critical polymer discovery problem that requires enormous experimental efforts where Machine learning (ML) approaches can help to reduce such efforts. To this end, both supervised and unsupervised ML approaches are developed to predict the proton conductivity of SPIs. A hybrid dataset of 81 unique SPIs is generated that consists of collected chemical structure–properties data from reported literature and calculated quantitative structure–property and semi-empirical quantum chemical descriptors. Using simple and interpretable Decision Trees, rules that lead to a low or high class of proton conductivity labels with high accuracy are identified. The trained decision tree model can accurately predict the proton conductivity class labels with a prediction accuracy of 88% and a kappa statistic of 0.77. The random forest regression (RFR) model, on the other hand, identified additional set of features that can predict proton conductivity with reasonable error. Thus, high information-gain features have been identified and their correlation with the proton conductivity class labels have been explored. These findings are key to designing novel SPI PEMs while correlating proton transport at the ionomer level with factors such as the morphology of the microstructure and inter-chain interactions. © 2022 Elsevier B.V.

Computational Materials Science

Designing sulfonated polyimide-based fuel cell polymer electrolyte membranes using machine learning approaches

The prevailing literature typically assesses the ef-fectiveness of Meta-learning (ML) approaches on tasks that involve no more than 20 classes. However, we challenge this convention by conducting a more complex and natural task setup to test the fundamental initialization, metric and optimization approaches. In particular, we increase the number of classes in the Omniglot and tieredImagenet datasets to 200 and 90, respectively. Interestingly, we observe that as the number of classes increases, ML approaches perform in reverse order of their degree of adaptation, with ProtoNet outperforming ANIL and MAML. ProtoNet, which does not require adaptation, is marginally affected by the increase in task complexity, while ANIL and MAML are highly affected. Despite performing full feature backbone and classifier adaptation, MetaLSTM&#x002B;&#x002B; exhibits an intriguing behavior of performing well. To this end, we analyze the backbone learned by different algorithms and the influence of adaptation from different perspectives. We uncover that ProtoNet learns better and MetaLSTM&#x002B;&#x002B; learns the worst backbone, but the generalizability to unseen data for MetaLSTM&#x002B;&#x002B; is compensated by powerful adaptation to the meta-test support sets, due to its learned data-driven optimizer. IEEE

IEEE Transactions on Artificial Intelligence

Adaptation: Blessing or Curse for Higher-way Meta-learning

This paper considers the problem of group fairness in clustering. We propose a new fairness notion which strictly generalizes existing notions and we theoretically analyze the relationships between several existing notions. Finally, we propose a simple and efficient greedy round-robin-based algorithm (FRACOE) and extensive experiments to validate its efficacy across multiple datasets. © 2023 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

Group Fair Clustering Revisited - Notions and Efficient Algorithm

Background: Adolescence and early adulthood are vulnerable periods for substance use-related disorders later in life. The use of internet-enabled interventions can be useful, especially in low-resource settings. Aims: To examine the feasibility, acceptability and preliminary effectiveness of single-session digital screening and brief intervention (d-SBI) for illicit drug misuse in college students and explore barriers and facilitators of d-SBI. Methods: Design: Mixed-methods, pilot cluster randomized trial. Setting: Four conveniently selected colleges were randomized into intervention and control groups. Participants: 219 students were screened and 37 fulfilled eligibility. Twenty-four completed follow-ups. In-depth interviews were done with ten students. Intervention and Comparator: Following a digital screening, Alcohol, Smoking and Substance Involvement Screening Test (ASSIST) based brief intervention was provided in the d-SBI group. The control group received brief education. Measurements: Acceptability was assessed by direct questions and usage statistics. ASSIST scores of groups were assessed at baseline and 3 months. Inductive coding of the interview transcript was done. Results: More than 50 % of participants found d-SBI user-friendly, appropriate and useful. Eighty percent of users, who logged in, completed screening. Per-protocol analysis showed a reduction in cannabis-ASSIST score over 3 months. The mean ASSIST score for other drugs combined did not differ significantly between groups. The difference in risk transition (moderate to low) was not significant. Qualitative analysis revealed three overarching themes- recruitment, engagement and behavior change. Conclusions: Digital SBI for drug misuse is feasible among college students. d-SBI might be effective in reducing cannabis use. © 2023 Elsevier B.V.

Asian Journal of Psychiatry

Digital screening and brief intervention for illicit drug misuse in college students: A mixed methods, pilot, cluster, randomized trial from India

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.

Data Mining and Knowledge Discovery

Efficient algorithms for fair clustering with a new notion of fairness

Clustering is a classical unsupervised machine learning technique. It has various applications in criminal justice, automated resume processing, bank loan approvals, recommender systems and many more. Despite being so popular, traditional clustering algorithms may result in discriminatory behavior towards a group of people (or individuals) and have societal impacts. It has led to the study of fair clustering algorithms that aim to minimize the clustering cost while ensuring fairness. This chapter outlines existing group and individual fairness notions, discusses their relationships and comprehensively categorizes the current algorithms. The chapter further discusses the advantages and disadvantages of existing algorithms in terms of theoretical guarantees, time complexity and reproducibility. Finally, the chapter concludes with a discussion of new directions and open problems in the field of fair clustering. © The Institution of Engineers (India) 2023.

Studies in Computational Intelligence

Group and Individual Fairness in Clustering Algorithms

Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers). In a real-life scenario, obtaining sample images for all possible words is also not feasible. However, zero-shot learning methods could aptly be used to recognize unseen/out-of-lexicon words in such historical document images. Based on previous state-of-the-art method for zero-shot word recognition “Pho(SC)Net”, we propose a hybrid model based on the CTC framework (Pho(SC)-CTC) that takes advantage of the rich features learned by Pho(SC)Net followed by a “connectionist temporal classification” (CTC) framework to perform the final classification. Encouraging results were obtained on two publicly available historical document datasets and one synthetic handwritten dataset, which justifies the efficacy of Pho(SC)-CTC and Pho(SC)Net. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

International Journal on Document Analysis and Recognition

Pho(SC)-CTC—a hybrid approach towards zero-shot word image recognition

The growing privacy concerns and the communication costs associated with transmitting raw data have resulted in techniques like federated learning, where the machine learning models are trained at the edge nodes and the parameter updates are shared with a central server. Because communications from the edge nodes are often unreliable, a hierarchical setup involving intermediate helper nodes is considered. The communication links between the edges and the helper nodes are error-prone and are modeled as straggling/failing links. To overcome the issue of link failures, coding techniques are proposed. The edge nodes communicate encoded versions of the model updates to the helper nodes, which pass them on to the master after suitable aggregation. The primary work in this area uses repetition codes and Maximum Distance Separable (MDS) codes at the edge nodes to arrive at the Aligned Repetition Coding (ARC) and Aligned MDS Coding (AMC) schemes, respectively. We propose using vector codes, specifically a family of layered MDS codes parameterized by a variable ?, at the edge nodes. For the proposed family of codes, suitable aggregation strategies at the helper nodes are also developed. At the extreme values of ?, our scheme matches the communication costs incurred by the ARC and AMC schemes, resulting in a graceful transition between these schemes. © 2023 IEEE.