Publications

Refereed Conference Publications

J. Brophy and D. Lowd

Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees

NeurIPS 2022 (Acceptance rate: 26.5%)

J. Brophy and D. Lowd

Machine Unlearning for Random Forests

ICML 2021 (Acceptance rate: 21.5%)

Refereed Journal Publications

J. Brophy, Z. Hammoudeh, and D. Lowd

Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees

JMLR (Acceptance rate: ~20%)

Refereed Workshop Publications

J. Brophy, D. Lowd

Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees

Workshop on Distribution-Free Uncertainty Quantification (DFUQ, co-located with ICML), 2022

 Z. Xie, J. Brophy, A. Noack, W. You, K. Asthana, C. Perkins, S. Reis, Z. Hammoudeh, D. Lowd, S. Singh, 

What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations

Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP, co-located with EMNLP), 2021

J. Brophy and D. Lowd

DART: Data Addition and Removal Trees

Workshop on Privacy-Preserving AI (PPAI, co-located with AAAI) 2021

J. Brophy and D. Lowd

TREX: Tree-Ensemble Representer-Point Explanations

Workshop on Extending Explainable AI Beyond Deep Models and Classifiers (XXAI, co-located with ICML), 2020

J. Brophy and D. Lowd

EGGS: A Flexible Approach to Relational Modeling of Social Network Spam

Workshop on Statistical Relational Learning in AI (STARAI, co-located with AAAI), 2020

J. Brophy and D. Lowd

Collective Classification of Social Network Spam

Workshop on Artificial Intelligence for Cyber Security (AICS, co-located with AAAI), 2017

For a complete list, visit Google Scholar.