Niloy Ganguly
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Niloy Ganguly has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
- Pawan Goyal
Indian Institute of Technology Kharagpur
11 shared publications - Arijit Nag
IIT Kharagpur IIT Kharagpur IIT Kharagpur IIT Bombay
6 shared publications - Bidisha Samanta
IIT Kharagpur
6 shared publications - Soumen Chakrabarti
IIT Bombay, Mumbai, India
6 shared publications - Animesh Mukherjee
Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India
5 shared publications - Subhendu Khatuya
Indian Institute of Technology Kharagpur India
5 shared publications
Latest Publications
- Open Access
- 20 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (5) , 1-54
A Survey on Signed Network Reconstruction Modeling and Its Applications
The proliferation in the use of Online Social Networks has revolutionized information sharing and consumption, leading to the development of advanced techniques such as link prediction, recommendation systems, community detection, node classification, and network representation learning. However, the availability and quality of real-world datasets for testing these algorithms pose challenges. Synthetic signed datasets generated through signed network reconstruction models offer alternatives for algorithm testing and experimentation. This survey presents an overview of state-of-the-art signed network reconstruction modeling techniques, evaluates their performance through rigorous experimental analysis, explores real-world applications, discusses challenges and open research problems, and guides future research efforts in the field. By consolidating knowledge and providing insights into existing models, this survey contributes to advancing the understanding and improvement of signed network reconstruction modeling. Various research papers discussed in this survey along with publicly available links to their codes are available at: https://github.com/Aikta-Arya/Signed-Network-Reconstruction-Modeling .
- 20 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (5) , 1-54
Open AccessA Survey on Signed Network Reconstruction Modeling and Its Applications
The proliferation in the use of Online Social Networks has revolutionized information sharing and consumption, leading to the development of advanced techniques such as link prediction, recommendation systems, community detection, node classification, and network representation learning. However, the availability and quality of real-world datasets for testing these algorithms pose challenges. Synthetic signed datasets generated through signed network reconstruction models offer alternatives for algorithm testing and experimentation. This survey presents an overview of state-of-the-art signed network reconstruction modeling techniques, evaluates their performance through rigorous experimental analysis, explores real-world applications, discusses challenges and open research problems, and guides future research efforts in the field. By consolidating knowledge and providing insights into existing models, this survey contributes to advancing the understanding and improvement of signed network reconstruction modeling. Various research papers discussed in this survey along with publicly available links to their codes are available at: https://github.com/Aikta-Arya/Signed-Network-Reconstruction-Modeling .
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. PP (3) , 1-16
SLAB: A Self-supervised Label Generation Framework to Reduce Annotation Overhead
Recently, many emotion-aware services have been designed to improve the user experience during online video consumption (e.g., online meeting platforms, and online tutoring mediums). These services primarily deploy a machine learning model that infers user emotion continuously based on the variation in different physiological signals . However, the major challenge to developing such models is to continuously ask the users to self-report their emotions for ground truth annotation. To address these challenges, we present SLAB (Self-supervised LABel generator), a self-supervised deep learning framework for label generation to reduce the tabular data annotation overhead. SLAB utilizes two pretext tasks coupled with a novel $log-cosh$ loss function to learn useful representations from unlabeled data that apply to the downstream task of label generation. SLAB outperforms supervised learning, semi-supervised learning, and self-supervised learning baselines such as Value Imputation and Mask Estimation (VIME) on continuous emotion annotation datasets - Continuously Annotated Signals of Emotion (CASE) and K-EmoCon. We also demonstrate the generalizability of the SLAB on a unique wheelchair surface vibration dataset (in addition to four publicly available datasets from different domains). These findings highlight that SLAB significantly reduces the annotation overhead in situations where the number of unlabeled samples vastly outnumbers labeled samples.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. PP (3) , 1-16
SLAB: A Self-supervised Label Generation Framework to Reduce Annotation Overhead
Recently, many emotion-aware services have been designed to improve the user experience during online video consumption (e.g., online meeting platforms, and online tutoring mediums). These services primarily deploy a machine learning model that infers user emotion continuously based on the variation in different physiological signals . However, the major challenge to developing such models is to continuously ask the users to self-report their emotions for ground truth annotation. To address these challenges, we present SLAB (Self-supervised LABel generator), a self-supervised deep learning framework for label generation to reduce the tabular data annotation overhead. SLAB utilizes two pretext tasks coupled with a novel $log-cosh$ loss function to learn useful representations from unlabeled data that apply to the downstream task of label generation. SLAB outperforms supervised learning, semi-supervised learning, and self-supervised learning baselines such as Value Imputation and Mask Estimation (VIME) on continuous emotion annotation datasets - Continuously Annotated Signals of Emotion (CASE) and K-EmoCon. We also demonstrate the generalizability of the SLAB on a unique wheelchair surface vibration dataset (in addition to four publicly available datasets from different domains). These findings highlight that SLAB significantly reduces the annotation overhead in situations where the number of unlabeled samples vastly outnumbers labeled samples.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP, 1-13
IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction
Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user tasks. But every system has its own limitations. There are instances where even for known intents, if any model exhibits low confidence, it results in rejection of utterances that necessitate manual annotation. Additionally, as time progresses, there may be a need to re-train these agents with new intents from the system-rejected queries to carry out additional tasks. Labeling all these emerging intents and rejected utterances over time is impractical, thus calling for an efficient mechanism to reduce annotation costs. In this paper, we introduce IDALC (Intent Detection and Active Learning based Correction), a semi-supervised framework designed to detect user intents and rectify system-rejected utterances while minimizing the need for human annotation. Empirical findings on various benchmark datasets demonstrate that our system surpasses baseline methods, achieving a ç5-10% higher accuracy and a ç4-8% improvement in macro-F1. Remarkably, we maintain the overall annotation cost at just ç6-10% of the unlabelled data available to the system. The overall framework of IDALC is shown in Fig. 1.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP, 1-13
IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction
Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user tasks. But every system has its own limitations. There are instances where even for known intents, if any model exhibits low confidence, it results in rejection of utterances that necessitate manual annotation. Additionally, as time progresses, there may be a need to re-train these agents with new intents from the system-rejected queries to carry out additional tasks. Labeling all these emerging intents and rejected utterances over time is impractical, thus calling for an efficient mechanism to reduce annotation costs. In this paper, we introduce IDALC (Intent Detection and Active Learning based Correction), a semi-supervised framework designed to detect user intents and rectify system-rejected utterances while minimizing the need for human annotation. Empirical findings on various benchmark datasets demonstrate that our system surpasses baseline methods, achieving a ç5-10% higher accuracy and a ç4-8% improvement in macro-F1. Remarkably, we maintain the overall annotation cost at just ç6-10% of the unlabelled data available to the system. The overall framework of IDALC is shown in Fig. 1.
- Open Access
Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting guide LLMs through intermediate reasoning steps. Although in-context learning with few-shot prompting has improved performance, LLMs still lag behind state-of-the-art models on financial numerical reasoning datasets such as FinQA and ConvFinQA. In this work, we introduce FINDER, a novel two-step framework, to enhance LLMs' capabilities in financial numerical reasoning. The first step utilizes a generative retriever to extract relevant facts from unstructured data, including both text and tables. This is followed by context-aware Program of Thought prompting with dynamic selection of in-context examples. Our model FINDER achieves a new state-of-the-art performance on both the FinQA and ConvFinQA datasets, surpassing previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.
Open AccessProgram of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting guide LLMs through intermediate reasoning steps. Although in-context learning with few-shot prompting has improved performance, LLMs still lag behind state-of-the-art models on financial numerical reasoning datasets such as FinQA and ConvFinQA. In this work, we introduce FINDER, a novel two-step framework, to enhance LLMs' capabilities in financial numerical reasoning. The first step utilizes a generative retriever to extract relevant facts from unstructured data, including both text and tables. This is followed by context-aware Program of Thought prompting with dynamic selection of in-context examples. Our model FINDER achieves a new state-of-the-art performance on both the FinQA and ConvFinQA datasets, surpassing previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (1) , 612-627
Multicalibration in Fair Link Prediction
In this work, we expand the multicalibration fairness metric to graph-structured data. Machine learning models, including graph neural networks (GNNs), have been demonstrated to generate unfair results when trained on data containing biases towards certain demographic groups. Consequently, several fairness enhancing methods have been proposed to deal with such biases in the model predictions. To evaluate the performance of these methods, metrics such as demographic parity and equalized odds have been proposed, which aim to ensure equal treatment across groups. However, these metrics do not take into consideration the diverse underlying distribution of the data across the different demographic groups. Hence, fairness is only achieved at the cost of utility. Multicalibration, on the other hand, aims to generate calibrated predictions for each group, thereby providing much stronger fairness guarantees. However, multicalibration is only defined for tabular data. Consequently, in this work, we provide a novel formulation of multicalibration fairness metric for graph-structured data, specifically for the task of link prediction. We demonstrate that the existing fairness enhancing methods are unable to achieve multicalibration, which leads us to define a simple quadratic program-based postprocessing method. Experiments across several real-world datasets demonstrate the effectiveness of our method, consistently outperforming the existing approaches. Our method is model agnostic and can seamlessly adapt to scenarios with single or multiple sensitive attributes.
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 13 (1) , 612-627
Multicalibration in Fair Link Prediction
In this work, we expand the multicalibration fairness metric to graph-structured data. Machine learning models, including graph neural networks (GNNs), have been demonstrated to generate unfair results when trained on data containing biases towards certain demographic groups. Consequently, several fairness enhancing methods have been proposed to deal with such biases in the model predictions. To evaluate the performance of these methods, metrics such as demographic parity and equalized odds have been proposed, which aim to ensure equal treatment across groups. However, these metrics do not take into consideration the diverse underlying distribution of the data across the different demographic groups. Hence, fairness is only achieved at the cost of utility. Multicalibration, on the other hand, aims to generate calibrated predictions for each group, thereby providing much stronger fairness guarantees. However, multicalibration is only defined for tabular data. Consequently, in this work, we provide a novel formulation of multicalibration fairness metric for graph-structured data, specifically for the task of link prediction. We demonstrate that the existing fairness enhancing methods are unable to achieve multicalibration, which leads us to define a simple quadratic program-based postprocessing method. Experiments across several real-world datasets demonstrate the effectiveness of our method, consistently outperforming the existing approaches. Our method is model agnostic and can seamlessly adapt to scenarios with single or multiple sensitive attributes.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (17) , 17822-17830
ExPERT: Modeling Human Behavior Under External Stimuli Aware Personalized MTPP
Marked Temporal Point Process (MTPP) -- the de-facto sequence model for continuous-time event sequences -- historically employed for modeling human-generated action sequences, lack awareness of external stimuli. In this study, we propose a novel framework developed over Transformer Hawkes Process (THP) to incorporate external stimuli in a domain-agnostic manner. Furthermore, we integrate personalization into our framework by employing language model-based representations of user and event descriptions, which is essential for modeling human-generated action sequences. Towards evaluating the efficacy, we put together a comprehensive benchmark comprising 5 datasets (2 novel additions, and 3 repurposed from existing open datasets) harvested from several domains, spanning education, e-commerce, online payment, and discussion forum. On average, we achieve 9.35% gain in type-prediction accuracy and 7.38% reduction in time-prediction RMSE across all datasets over SOTA MTPP baselines. We demonstrate the superior performance of our proposed model through extensive ablations and showcasing its ability to capture complex combinations of external stimuli in a synthetic set up.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (17) , 17822-17830
Open AccessExPERT: Modeling Human Behavior Under External Stimuli Aware Personalized MTPP
Marked Temporal Point Process (MTPP) -- the de-facto sequence model for continuous-time event sequences -- historically employed for modeling human-generated action sequences, lack awareness of external stimuli. In this study, we propose a novel framework developed over Transformer Hawkes Process (THP) to incorporate external stimuli in a domain-agnostic manner. Furthermore, we integrate personalization into our framework by employing language model-based representations of user and event descriptions, which is essential for modeling human-generated action sequences. Towards evaluating the efficacy, we put together a comprehensive benchmark comprising 5 datasets (2 novel additions, and 3 repurposed from existing open datasets) harvested from several domains, spanning education, e-commerce, online payment, and discussion forum. On average, we achieve 9.35% gain in type-prediction accuracy and 7.38% reduction in time-prediction RMSE across all datasets over SOTA MTPP baselines. We demonstrate the superior performance of our proposed model through extensive ablations and showcasing its ability to capture complex combinations of external stimuli in a synthetic set up.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1122-1123
Disinformation and Misinformation in the Age of Generative AI
The rapid rise of generative AI (GenAI) technologies has revolutionized the way content is created and disseminated. As a result, highly convincing human-like malicious content including disinformation, misinformation, and propaganda can now be easily produced and distributed across the web. The diversity of generation models combined with various manipulation strategies applied to different modalities presents significant challenges for fact-checking systems and content moderation. To address this issue, we organize a workshop that focuses on harmful content that has been created intentionally (disinformation) and unintentionally (misinformation) in the era of generative AI. The workshop features specialized tracks on multimodal solutions, investigating narratives, trustworthy AI systems, and policy interventions. By bringing together experts from computer science and law, the workshop offers a comprehensive framework for combating fake content online.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1122-1123
Open AccessDisinformation and Misinformation in the Age of Generative AI
The rapid rise of generative AI (GenAI) technologies has revolutionized the way content is created and disseminated. As a result, highly convincing human-like malicious content including disinformation, misinformation, and propaganda can now be easily produced and distributed across the web. The diversity of generation models combined with various manipulation strategies applied to different modalities presents significant challenges for fact-checking systems and content moderation. To address this issue, we organize a workshop that focuses on harmful content that has been created intentionally (disinformation) and unintentionally (misinformation) in the era of generative AI. The workshop features specialized tracks on multimodal solutions, investigating narratives, trustworthy AI systems, and policy interventions. By bringing together experts from computer science and law, the workshop offers a comprehensive framework for combating fake content online.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1012-1015
Building Trustworthy AI Models for Medicine: From Theory to Applications
AI is emerging as an efficient companion in medicine. While AI holds promise for reducing the cognitive load of researchers and practitioners, its adoption is often hindered by a lack of trust in new AI advancements. We present sophisticated techniques for developing trustworthy artificial intelligence (AI) models in medicine, bridging breakthroughs in AI research with practical healthcare applications. We will discuss in-depth the four stages (Design, Development, Implementation, and Evaluation) involved in the process of building trustworthy AI models customized for the medical domain. We present various techniques for incorporating important Trustworthy AI principles like data privacy, robustness, explainability, interpretability, medical experts-in-the-loop, and risk assessment while developing AI models for medicine. In contrast to prior tutorials, we make the following two key contributions: (i) While explaining the 'Implementation' stage, we cover various real-world healthcare applications developed as part of research projects in academia in collaboration with medical schools in India and Germany. (ii) By including a health informatics professional as one of the tutorial organizers, we provide a fresh and much-needed perspective on the research challenges and mitigation strategies in building AI models for medicine.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1012-1015
Open AccessBuilding Trustworthy AI Models for Medicine: From Theory to Applications
AI is emerging as an efficient companion in medicine. While AI holds promise for reducing the cognitive load of researchers and practitioners, its adoption is often hindered by a lack of trust in new AI advancements. We present sophisticated techniques for developing trustworthy artificial intelligence (AI) models in medicine, bridging breakthroughs in AI research with practical healthcare applications. We will discuss in-depth the four stages (Design, Development, Implementation, and Evaluation) involved in the process of building trustworthy AI models customized for the medical domain. We present various techniques for incorporating important Trustworthy AI principles like data privacy, robustness, explainability, interpretability, medical experts-in-the-loop, and risk assessment while developing AI models for medicine. In contrast to prior tutorials, we make the following two key contributions: (i) While explaining the 'Implementation' stage, we cover various real-world healthcare applications developed as part of research projects in academia in collaboration with medical schools in India and Germany. (ii) By including a health informatics professional as one of the tutorial organizers, we provide a fresh and much-needed perspective on the research challenges and mitigation strategies in building AI models for medicine.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 30994-31006
Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 30994-31006
Open AccessProgram of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22082-22092
MutantPrompt: Prompt Optimization via Mutation Under a Budget on Modest-sized LMs
Arijit Nag, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22082-22092
Open AccessMutantPrompt: Prompt Optimization via Mutation Under a Budget on Modest-sized LMs
Arijit Nag, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti. Findings of the Association for Computational Linguistics: ACL 2025. 2025.