👋 Hi there, I'm Michele (pirroh) Catasta
‼️ News
[Apr 2022] PaLM: Scaling Language Modeling with Pathways has just been unveiled -- I worked on PaLM-Coder! [paper] - [blog post]
[Mar 2021] Language-Agnostic Representation Learning of Source Code from Structure and Context (AKA Code Transformer) accepted at ICLR 2021! [paper] - [demo] - [code]
[Sep 2020] Open Graph Benchmark: Datasets for Machine Learning on Graphs accepted at NeurIPS 2020 as a spotlight paper! [paper] - [website] - [code]
🔦 Highlights
- Postdoc in Machine Learning at Stanford University
- Advised by Prof. Jure Leskovec
- Affiliated with SNAP and Statistical Machine Learning Group
- PhD in Computer Science at EPFL
- Research Scientist at Stanford University and at EPFL
- Contributed to several projects (funded by IARPA, DARPA, Samsung, Google, Amazon, ...) with a focus on Machine Learning (GNNs, Transformers, Open Graph Benchmark, etc.), Recommender Systems, Crowdsourcing, and Data Science.
- Intern at MIT Media Lab (w/ Prof. Alex 'Sandy' Pentland), Yahoo Research (w/ Prof. Ricardo Baeza-Yates), and Google.
- Founding member of Sindice.com, the largest Semantic Web Search Engine (back in the days). The core technologies developed for Sindice evolved into:
- At Stanford University:
- CS224W: Machine Learning with Graphs -- Co-instructor together with Prof. Jure Leskovec
- CS246: Mining Massive Data Sets -- Co-instructor together with Prof. Jure Leskovec
- CS329S: Machine Learning Systems Design -- Advisor
- CS341: Project in Mining Massive Data Sets -- Instructor
- At EPFL:
- Applied Data Analysis -- Created and taught the first edition of the course
- ADA is now taught by my friend and research collaborator Prof. Robert West (head of the Data Science Lab), who masterfully improved the course in several areas
- 2nd largest course offered by the CS department at EPFL, recently grown to ~400 students -- kudos to Bob
👍
- Applied Data Analysis -- Created and taught the first edition of the course