I build fast, scalable algorithms and systems for graphs. My flagship work, Highway, detects overlapping communities in networks up to 1.13 million nodes using sparse backbones — and is now integrated into cdlib, a mainstream community-detection library.
I'm currently finishing my MEng at the University of Toronto and applying to CS/EECS PhD programs for Fall 2027. My research interests lie in scalable graph algorithms, interpretable structural representations, and methods for making model decisions more traceable — as well as in the connection between graph theory and real-world problems.
I would also like to express my sincere gratitude to Prof. Samin Aref for his mentorship and guidance throughout my graduate studies. His support, encouragement, and trust have played a central role in my development as a researcher and in shaping the direction of my work.
News
- Sep 2026 Journal extension in preparation for SNAM.
- Now
- Sep 2026 Released DSEG-Char — a character-level poetry model that generates as a walk over a semantic graph.code
- Sep 2026 Released the Scout code.code
- Sep 2026 Scout — budgeted task-aware acquisition on dynamic networks, on arXiv.preprint
- Aug 2026 Co-presented Highway with Prof. Samin Aref at ASONAM 2026.
- Aug 2026 Gave an oral presentation on Highway at UTERC 2026 (Intelligent Systems and Data track).
- Aug 2026 Gave a talk on Highway at Complex Systems Day, Toronto Metropolitan University.
- Jul 2026 Highway to appear at ASONAM 2026 (Springer proceedings).accepted
- Jul 2026 Highway integrated into cdlib.
- Jun 2026 Presented at WAW 2026 — talk recording.
- May 2026 Poster at the MIE Graduate Research Symposium, Hart House Great Hall.
- Mar 2026 Featured in a University of Toronto MIE article on the Data Analytics & ML MEng.
Publications
Budgeted Task-Aware Acquisition of Dynamic Networks
Preprint, Sep 2026 · arXiv:2609.05862 · single-authored
Scout learns the task value of querying each node, so a limited observation budget refreshes what matters downstream rather than what changed most. Highest mean downstream performance in 19 of the 21 benchmark-budget settings.
Overlapping Network Community Detection Using Sparse Backbones
ASONAM 2026 (Springer proceedings) · Presented · co-presented with Prof. Samin Aref, Aug 2026
A four-step sparse-backbone method. Evaluated on ~3,000 synthetic graphs and three real SNAP networks (up to 1.13M nodes / 2.99M edges); the only method to finish all three within 300s (7.34× faster on the largest instance).
Triad: Suppressing Structural Degeneracy in Overlapping Community Detection
WAW 2026 · Presentation
A QCP formulation with node/edge/community constraints that explicitly suppresses structural degeneracy — the predecessor method that led to Highway.
Selected Research
One arc — structural reliability → scalability → what is worth observing → interpretability.
Triad
Structurally reliable overlapping assignments through node/edge/community constraints — precise but hard to scale.
Read the case study → FlagshipHighway
Scalable overlapping community detection through sparse structural backbones — to 1.13M nodes.
Read the case study → IndependentScout
Learning which stale graph information is worth refreshing — task utility, not freshness, decides where a limited observation budget goes.
Read the case study → IndependentDSEG
A character-level poetry model built as a walk over a 5,000-node graph — every step reports which term, state, edge or context, selected that character.
Read the DSEG model →Talks & Presentations
Triad
-
WAW 2026 Jun 18, 2026
Highway
-
ASONAM 2026 Aug 24-27, 2026Co-presented with Prof. Samin Aref · IEEE/ACM ASONAM 2026
-
UTERC 2026 Aug 21, 2026Conference talk (oral), in person · Intelligent Systems and Data track
-
Complex Systems Day Aug 12, 2026Talk · Toronto Metropolitan University
-
MIE Graduate Research Symposium May 4, 2026Poster · Hart House Great Hall, University of Toronto · selected for the MIE hallway display · Poster
Formal Training
Degrees, selected relevant coursework, and grades.
M.Eng., Mechanical & Industrial Engineering — Data Analytics & Machine Learning · 2025–2026
Research advised by Prof. Samin Aref.
- Foundations of Data Analytics and Machine LearningA+
- Data Science Methods and Statistical LearningA+
- Introduction to Machine LearningA+
- Cloud-Based Data AnalyticsA+
- Positive Psychology for EngineersA+
- Artificial Intelligence in FinanceA-
- Introduction to Reinforcement LearningIn progress
- MEng Research ProjectA+
B.C.S. — Computer Science Major · Artificial Intelligence Specialization · Computational Mathematics Minor · 2020–2025