Ph.D. Candidate

Penn State University

Biography

Hello! My name is Hangzhi Guo (郭杭之 | Birkhoff). I am a Ph.D. candidate in the College of Information Sciences and Technology (IST) at Penn State University advised by Dr. Amulya Yadav. I graduated from Wenzhou-Kean University majoring Computer Science.

I am broadly interested in human-centered machine learning and AI for Social Good. My current focus is to develop actionable and robust Explainable Machine Learning models (e.g., CounterNet, RoCourseNet). I am also devoted to applying techniques in machine learning and human-computer interaction to help under-served groups (including low-resource farmers, maternal mothers, children with autism). Media coverage of these works includes ThePrint.in, News Medical Life Sciences, and Penn State News.

In 2022, I founded and organized the Penn State CSRAI Young Achievers Symposium.

News

📢 Unveiling ReLax v0.2 🎉 - A JAX-based recourse explanation library designed for efficiency and scalability [ GitHub] [ Twitter].

Interests

  • Explainable AI
  • AI for Social Good
  • Human-centered Machine Learning
  • Deep Learning

Education

  • Ph.D. in Informatics, 2020 - Present

    Pennsylvania State University

  • BSc in Computer Science, 2016 - 2020

    Wenzhou-Kean University

Publications

See Google Scholar for all publications.

Selected Papers

(2023). RoCourseNet: Robust Training of a Prediction Aware Recourse Model. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM ’23).

PDF DOI Arxiv

(2023). CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’23).

PDF Code Slides Poster Twitter Workshop DOI

 Best Paper Runner-up Award @ICML-21 Workshop on Recourse

Recent Posts

A Collection of Research Resources on Explainable Machine Learning

I create a repository collecting a list of awesome research papers on Explainable Machine Learning.

Emerging Trends in Applied Deep Learning Research

A state-of-the-art report for non-tech readers.
Emerging Trends in Applied Deep Learning Research