Projects & Research

A Performance Intelligence Engine that analyzes and verifies algorithmic performance before code reaches production.

Automated forensic data collection toolkit for Unix systems. Arctic Code Vault Contributor ❄️.

Focus: Influence maximization, source localization, and graph neural networks.

• Deep graph representation learning influence maximization with accelerated inference
  Neural Networks (Elsevier), 2024
• Source Localization for Cross Network Information Diffusion
  Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024
• MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization
  27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
• DeepGAR: Deep Graph Learning for Analogical Reasoning
  IEEE International Conference on Data Mining (ICDM), 2022

Focus: Applied cryptography, VLSI timing analysis, and secure biometric sketches.

• RAPTA: A Hierarchical Representation Learning Solution For Real-Time Prediction of Path-Based Static Timing Analysis
  Proceedings of the Great Lakes Symposium on VLSI (GLSVLSI), 2022
• Multisketches: Practical secure sketches using off-the-shelf biometric matching algorithms
  ACM SIGSAC Conference on Computer and Communications Security (CCS), 2019

Focus: Forecasting events in dynamic environments (Healthcare, Spatial data).

• Deep Multi-task Learning for Spatio-Temporal Incomplete Qualitative Event Forecasting
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024
• Modeling Health Stage Development of Patients with Dynamic Attributed Graphs in Online Health Communities
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022
• Effects of electrode position on spatiotemporal auditory nerve fiber responses: A 3D computational model study
  Computational and Mathematical Methods in Medicine, 2015

Focus: Major survey papers on LLMs and Neural Reasoning.

• Knowledge-enhanced Neural Machine Reasoning: A Review
  arXiv preprint arXiv:2302.02093, 2023
• Domain specialization as the key to make large language models disruptive: A comprehensive survey
  ACM Computing Surveys, 2025