Research Experience

Research Interests

Design & Analysis of Algorithms Graph Theory & its applications Combinatorial Algorithms Social Networks Analysis Computational Social Science Complex Networks Data Structures & Databases Graph Mining Applied Machine Learning

Graduate Research Assistant

Graduate level · Concordia University, Algorithms & Complexity Lab, Department of Computer Science and Software Engineering · Montreal, Québec, Canada ·

  • Researching Algorithms Design & Analysis, Graph Theory, and Social Network Analysis
  • Working in the Algorithms & Complexity Lab
  • Under the supervision of Professor Hovhannes Harutyunyan
  • Date: Aug 2024 – Now
  • My key role consisted of:
    • Designed Spider, a graph community detection algorithm combining geodesic expansion, modularity-guided refinement, and greedy merge matching.
    • Benchmarked Spider against Louvain, Leiden, Infomap, CNM, and Label Propagation on nine real-world networks (34–8,035 vertices) and LFR benchmarks, achieving top F1 and ARI on Karate Club and Political Blogs and NMI 0.88 on Primary School, where flow- and propagation-based baselines collapse to near-trivial partitions.
    • Introduced Weighted Average Geodesic Distance Modularity (wGDM), a size-consistent, label-free partition quality measure.
    • Conducted the first systematic study of metric backbone sparsification with Leiden, achieving 14–71% edge reduction across seven networks while preserving — and on dense contact networks improving — detection quality (High School F1: 0.834 → 0.970).
    • Built a fully reproducible experimental pipeline with fixed random seeds, baseline implementations, and automated evaluation scripts.
  • We have published two papers so far: the IEEE SNAMS 2025 Conference[1] and the Computers Journal[2]

Remote Research Assistant

Graduate level · University of Twente, Faculty of EE, Math and CS - FMT group: Formal Methods and Tools · Enschede, The Netherlands ·

  • Working and collaborating with the “Electrical Engineering, Mathematics and Computer Science” department of “University of Twente”.
  • Field of Research: Software Refactoring
  • Research Group: FMT group - Formal Methods and Tools
  • Date: Aug 2023 – March 2024
  • Supervisor: Dr. Iman Hemati Moghadam
  • My key role consisted of:
    • Implemented the KotlinCode2Text parser and integrated it into the RefDetect framework for automated refactoring detection.
    • Constructed two refactoring datasets used for empirical evaluation in the SANER 2024 study.
    • Improved analysis reliability and runtime through targeted debugging and algorithmic refinements.
    • Investigated LLM-based prompt engineering for cross-language code translation in refactoring mining.
    • Contributed to the XlateRefactor pipeline, evaluated across 241 commits and 71 repositories with ~2,000 validated refactorings in Java, Kotlin, and C, with all artifacts released publicly.
  • We have published one paper in the IEEE SANER 2024 Conference[1]. Our second paper, “XlateRefactor: A Language-Agnostic Pipeline for Cross-Language Refactoring Detection Using LLM-Based Code Translation”, is currently under review at JSME (major revision).

Undergraduate Research Assistant

Undergraduate level · Vali-e-Asr University of Rafsanjan, Department of Computer Engineering · Rafsanjān, Kerman, Iran ·

  • Field of Research: Community Detection (Graph Algorithms)
  • Supervisor: Dr. Fahimeh Dabaghi-Zarandi
  • Department: “Computer Engineering” department of “Vali-e-Asr University of Rafsanjan”.
  • Date: Aug 2021 – March 2024
  • My key role consisted of:
    • Conducted a comprehensive review of prior work in graph-based community detection.
    • Designed and implemented CRLG, a randomized community detection framework leveraging both local and global network information.
    • Developed weighted probabilistic seeding and similarity-driven community assignment with heuristic community merging.
    • Implemented and evaluated the framework in MATLAB and Python, including validation, testing, and performance tuning.
    • Evaluated on real-world networks and GN/LFR benchmarks, achieving up to 10% improvement over LCDR, MOACO, Node2Vec-SC, NE-N2V, CDASS, and TS using NMI, modularity, and density metrics.
  • We have published one paper in the JNCA journal[1] (Q1), which has been cited 25+ times.