Our paper on ML auditing via Fourier Analysis is accepted in AAAI 2025. This is a collaboration with Ayoub and Deb from Inria, France.
Our paper on reliable knowledge estimation in LLMs is accepted at WSDM, 2025. We propose a simple method that can reliably estimate the latent knowledge across multiple LLMs and relation queries.
Paper accepted on split learning for multi-modal medical image classification at IEEE CAI, 2024. Joint work with Yuan Wang, Huazhu Fu, Wei Qingsong, Yong Liu, and Rick Goh.
I have jointly presented a tutorial with Debabrota Basu on auditing fairness in machine learning at IJCAI 2023.
I have defended my Ph.D. thesis in NUS.
I am joining Institute of High Performance Computing (IHPC), A*STAR, Singapore as a scientist.
Our tutorial on "Auditing Bias of Machine Learning Algorithms: Tools and Overview" is accepted in IJCAI 2023. This is a joint work with Debabrota Basu.
My thesis abstract is accepted in IJCAI 2023 Doctoral Consortium. The title of the abstract is "Interpretability and Fairness in Machine Learning: A Formal Methods Approach".
Our work on "Neighborhood-based Hypergraph Core Decomposition" is accepted in VLDB 2023. This is a joint work with Naheed Anjum Arafat, Arijit Khan, and Arpit Kumar Rai.
Our work on "How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis" is accepted in FAccT 2023. This is a joint work with Debabrota Basu and Kuldeep S. Meel.
I have submitted my PhD thesis for examination in NUS. The title of the thesis is "Interpretability and Fairness in Machine Learning: A Formal Methods Approach".
I am visiting Max Planck Institute for Software Systems, Saarbrucken, Germany as a research fellow. I will be working with Prof. Krishna P. Gummadi.
Our work on Efficient Learning of Interpretable Classification Rules is published in Jair 2022. This is a joint work with Dmitry Malioutov and Kuldeep S. Meel.
Our work on Algorithmic Fairness Verification with Graphical Models is accepted in AAAI 2022. This is a joint work with Debabrota Basu and Kuldeep S. Meel.
I have been invited for a research visit to Inria, Lille Nord, France. I will be working with Debabrota Basu on fairness in Machine Learning.
Our paper on social-spatial group queries with keywords has been accepted in ACM Transactions on Spatial Algorithms and Systems (TSAS). This is a joint work with Sajid Hasan Apon, Mohammed Eunus Ali, and Timos Sellis.
We have improved fairness-verification for linear classifiers both in terms of accuracy and scalability. The paper is available in arXiv now.
I have completed my internship at Goldman Sachs. During my internship, I have experimented with recent advances in transformer-based models, such as BERT, in natural language processing (NLP).
I have joined Goldman Sachs, Singapore as an AI research intern.
Our work on formal fairness verification based on Stochastic Boolean Satisfiability (SSAT) is accepted in AAAI 2021. This is a joint work with Debabrota Basu and Kuldeep S. Meel.
Our work on explaining Recurrent Neural Networks using Linear Temporal Logic is now available in arXiv.
I have joined Max Planck Institute for Software Systems as a research fellow. I am working on explanations of neural networks using formal languages with Daniel Neider.
Our AIES-19 paper on incremental classification rule learning is accepted as a poster presentation with a spollight talk at StarAI 2020 workshop in AAAI 2020.
Blog released on our paper on an incremental approach to interpretable classification rule learning.
An abstract on Incremental Approach to Interpretable Classification Rule Learning is accepted in CP 2019.
We have designed an interpretable rule-based classifier that generates decisions in the form of a richer family of logical rules, namely relaxed-CNF rule. The paper is accepted at IJCAI workshop on XAI (Explainable Artificial Intelligence) and DSO (Data Science meets Optimization), 2019.
We have released a python library for generating interpretable decision rules in CNF. This library is based on our paper on incremental approach for learning decision rules.
My first paper during PhD on interpretable classification rules is accepted for publication at AIES 2019.
My undergrad thesis work on socio spatial group queries is accepted for publication at VLDB 2019.