Scholar
Bryan Perozzi
Google Scholar ID: rZgbMs4AAAAJ
Google Research
Citations & Impact
Citations
18,492
H-index
35
i10-index
53
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Paper 'Scalable Anomaly Ranking of Attributed Neighborhoods' awarded Best Paper Runner-up at SDM'16.
- - 'Ties That Bind: Characterizing Classes by Attributes and Social Ties' accepted at WWW'17 (Web Science Track).
- - 'When Recommendation Goes Wrong: Anomalous Link Discovery in Recommendation Networks' accepted at KDD'16.
- - 'Freshman or Fresher? Quantifying the Geographic Variation of Internet Language' accepted at ICWSM'16.
- - 'DeepWalk: Online Learning of Social Representations' accepted at KDD'14 (full paper acceptance rate: 14.6%).
- - 'Focused Clustering and Outlier Detection in Large Attributed Graphs' accepted at KDD'14 (full paper acceptance rate: 14.6%).
- - 2015 Catacosinos Fellowship for Excellence in Computer Science (awarded to the top PhD students in the department).
- - 2014 Junior Researcher Fellowship from the Institute for Advanced Computational Science (IACS) at Stony Brook University.
Research Experience
- Works in the areas of data mining and knowledge discovery, machine learning, network science, and natural language processing.
Background
- Research interests include data mining, graph mining, graph theory, distributed algorithms, natural language processing, and machine learning. Particularly interested in local graph algorithms.
Miscellany
- Projects:
- - DeepWalk: Uses deep learning techniques to learn representations of graphs for semi-supervised learning problems.
- - Focused Clustering: Examines user-oriented clustering and anomaly detection in attributed graphs.
- - Inducing Language Networks: Investigates making meaningful language networks from distributed word representations.
- - Polyglot: A publicly available repository of word embeddings for over 100 languages.
Co-authors