Publications

2024

1. NeurIPS

   Improving Decision Sparsity

   Yiyang Sun, Tong Wang, and Cynthia Rudin

   Advances in Neural Information Processing Systems, 2024

2. AISTATS

   Sparse and Faithful Explanations Without Sparse Models

   Yiyang Sun, Zhi Chen, Vittorio Orlandi, Tong Wang, and Cynthia Rudin

   International conference on artificial intelligence and statistics, 2024

   Winner of Data Mining Best Paper Award, INFORMS, 2023.

2023

1. JMLR

   Interpretable Sequence Classification via Prototype Trajectory

   Dat Hong†, Tong Wang*, and Stephen Baek

   Journal of Machine Learning Research, 2023

   Code

2022

1. NeurIPS

   ProtoX: Explaining a Reinforcement Learning Agent via Prototyping

   Ronilo Ragodos†, Tong Wang*, Qihang Lin, and Xun Zhou

   Advances in Neural Information Processing Systems, 2022

2. SIGKDD

   AdaAX: Explaining Recurrent Neural Networks by Learning Automata with Adaptive States

   Dat Hong†, Alberto Maria Segre, and Tong Wang*

   In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022

2021

1. JMLR

   Hybrid Predictive Models: When an Interpretable Model Collaborates with a Black-box Model

   Tong Wang, and Qihang Lin

   The Journal of Machine Learning Research, 2021

2020

1. AISTATS

   Interpretable Companions for Black-box Models

   Danqing Pan, Tong Wang, and Satoshi Hara

   In International conference on artificial intelligence and statistics, 2020

2. ICML

   Transparency Promotion with Model-agnostic Linear Competitors

   Hassan Rafique, Tong Wang*, Qihang Lin, and Arshia Singhani

   In International Conference on Machine Learning, 2020

   Runner-up for Best Paper Award at INFORMS Workshop on Data Science, 2019.

2019

1. ICML

   Gaining Free or Low-cost Interpretability with Interpretable Partial Substitute

   Tong Wang

   In International Conference on Machine Learning, 2019

   Code

2018

1. NeurIPS

   Multi-value Rule Sets for Interpretable Classification with Feature-efficient Representations

   Tong Wang

   Advances in neural information processing systems, 2018

   Code

2017

1. JMLR

   A Bayesian Framework for Learning Rule Sets for Interpretable Classification

   Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, and Perry MacNeille

   The Journal of Machine Learning Research, 2017

   Code

2015

1. BigData

   Finding Patterns with a Rotten Core: Data Mining for Crime Series with Cores

   Tong Wang, Cynthia Rudin, Daniel Wagner, and Rich Sevieri

   Big Data, 2015

2013

1. ECMLKDD

   Learning to Detect Patterns of Crime

   Tong Wang, Cynthia Rudin, Daniel Wagner, and Rich Sevieri

   In Joint European conference on machine learning and knowledge discovery in databases, 2013

   This project is the Second place winner of “Doing Good with Good OR”, INFORMS, 2015 and is reported in several media including WIRED.com and Wiki Crime Analysis. Ideas from this work were implemented by the NYPD by Alex Chohlas-Wood and E.S. Levine in their algorithm Patternizr (Please see this paper for the implementation details), which operates live in New York City since 2019.

2. AAAI

   Detecting Patterns of Crime with Series Finder

   Tong Wang, Cynthia Rudin, Daniel Wagner, and Rich Sevieri

   In Proceedings of the 17th AAAI Conference on Late-Breaking Developments in the Field of Artificial Intelligence, 2013