Fabricio Murai (he/him)

Fabricio Murai (he/him)

Assistant Professor of CS & Data Science

Worcester Polytechnic Institute

Biography

Fabricio Murai is an Assistant Professor in Computer Science and Data Science at the Worcester Polytechnic Institute (WPI). His research lies in the application of mathematical modeling, statistics and machine learning to computer, informational and social networks. He has published in top scientific journals such as IEEE Journal of Selected Areas in Communications, Data Mining and Knowledge Discovery and ACM TKDD. He serves as a TPC member for the IEEE INFOCOM, ACM SIGKDD and WWW.

Download my CV.

Interests
  • Artificial Intelligence
  • Data Science
  • Complex Networks
Education
  • PhD in Computer Science, 2016

    University of Massachusetts Amherst

  • MSc in Computer Science, 2014

    University of Massachusetts Amherst

  • MSc in Systems and Comp. Engineering, 2011

    COPPE - Universidade Federal do Rio de Janeiro

  • BSc in Computer Science, 2007

    Universidade Federal do Rio de Janeiro

Projects

*
[2023] Mining graph patterns in software development from code repositories

[2023] Mining graph patterns in software development from code repositories

In this project, we will collect, model, and analyze code development repositories for pattern mining using graph and machine learning techniques.

[2018-2019] Artificial Intelligence for Spotting Fake Profiles and Anomalous Users’ Behaviors on the Web

A joint internationalization project between UFMG and PoliTO funded by Compagnia di San Paolo.
The key role of the web in our society requires mechanisms to guarantee its legitimate. Such mechanisms demand novel methodologies to cope with complex and multi-dimensional big data, for which ground truth is inherently lacking. We will build models that combine information from multiple sources (e.g., online social networks and network measurements) to uncover fake profiles and suspicious activities, enhancing the legitimate use of the web.

[2021-2024] WildPixels: Dense Labeling of Remote Sensing Images in the Wild

Awarded in Serrapilheira’s 4th Call.
Detection of illegal rural roads, location of areas with greater risk for dengue and identification of plant and animal species that indicate climate change.

[2019-2021] Next Generation Graph Embeddings

A research collaboration with Prof. Bruno Ribeiro (Purdue University) funded by CAPES/PrInt.
Deep learning has recently made great strides in solving increasingly complex tasks by simply mapping vector inputs to desired outputs. Still, the fundamental problem of building neural networks that can account for pre-defined input invariances of these vectors remains largely open.

[2017-2019] ATMOSPHERE - Adaptive, Trustworthy, Manageable, Orchestrated, Secure, Privacy-assuring, Hybrid Ecosystem for REsilient Cloud Computing

[2017-2019] ATMOSPHERE - Adaptive, Trustworthy, Manageable, Orchestrated, Secure, Privacy-assuring, Hybrid Ecosystem for REsilient Cloud Computing

ATMOSPHERE aims to design and implement a framework and platform relying on lightweight virtualization, hybrid resources and Europe and Brazil federated infrastructures to develop, build, deploy, measure and evolve trustworthy, cloud-enabled applications.

[2018-2020] Randomized Experiments in Social Networks

[2018-2020] Randomized Experiments in Social Networks

Novel algorithms and models for network A/B testing.

Recent Publications

Quickly discover relevant content by filtering publications.
(2022). Top-Down Deep Clustering with Multi-generator GANs. Proceedings of the AAAI Conference on Artificial Intelligence.

PDF Cite DOI

(2021). Quão efetivas são Redes Neurais baseadas em Grafos na Detecção de Fraude para Dados em Rede?. Anais do X Brazilian Workshop on Social Network Analysis and Mining.

PDF Cite DOI

(2021). Effects of population mobility on the COVID-19 spread in Brazil. PLOS ONE.

PDF Cite DOI

(2021). Encoding physical conditioning from inertial sensors for multi-step heart rate regression. ACM-CHIL Workshop.

Cite

(2021). Fairness via AI: Bias Reduction in Medical Information. FaccTRec@RecSys.

Cite

Contact

Teaching

In recent years, I have taught in the following courses:

Graduate-level:

  • Deep Learning: 2019/2, 2021/2, Fall 2022
  • Model Thinking: 2017/2, 2018/2, 2019/2
  • Seminar on Disinformation and Hate Speech in Digital Platforms: 2021/2
  • Seminar on Machine Learning for Graphs: 2019/2

Undergraduate-level:

Current/Former Students

Current MSc Students:

Current Undergrad Students (on REU program):

Former MSc Students:

Outreach

Residency Programs:

  • Usiminas: Techonological Residency in Data Science (2021-2022)
    Coordinator and Instructor

Training Programs:

  • PETROBRAS: Artificial Intelligence applied to Geosciences (2021-2024)
    Coordinator and Instructor

  • PETROBRAS: Introduction to Machine Learning (2020)
    Instructor

  • PETROBRAS: Artificial Intelligence applied to Geosciences (2019)
    Instructor

Microsoft Reactor Sao Paulo Workshops:

  • Data Science 1: Introduction to Python (Jul 1, 2020)
  • Data Science 1: Introduction to Numpy and Pandas (Jul 8, 2020)
  • First steps with Python (Oct 21, 2020)
  • Loan Qualification Predictor (Nov 18, 2020)
  • DS/ML: Linear Regression and Classification (Nov 25, 2020)
  • DS/ML: Random Forest - Human Activity Prediction (Dec 2, 2020)
  • Use the UNIX Shell to Wrangle Log Data (May 5, 2021)
  • Get Started with the Windows Subsystems for Linux (May 12, 2021)
  • Get Started with Vue (June 16, 2021)
  • Create Dynamic Pages in Vue.Js (June 23, 2021)
  • Vue CLI and Single-File Components in Vue.js (June 30, 2021)