Interpretable Learning

Interpretable learning aims to develop machine learning models that are not only accurate but also transparent and understandable, addressing the "black box" problem of many neural networks. Current research focuses on integrating symbolic reasoning with neural networks, employing architectures like rule-based systems, decision trees, and symbolic program representations enhanced by large language models, to create more explainable models. This pursuit is crucial for building trust in AI systems, particularly in high-stakes applications like autonomous driving and healthcare, where understanding model decisions is paramount for safety and accountability. Furthermore, improved interpretability facilitates easier debugging, model refinement, and knowledge transfer to human experts.

Papers

August 21, 2024

Neural Symbolic Logical Rule Learner for Interpretable Learning
Bowen Wei, Ziwei Zhu
Negation Detection Interpretable Classifier Rule Learning Learning Rule Symbolic Rule Interpretable Learning Discrete Activation

July 30, 2024

Beyond the Neural Fog: Interpretable Learning for AC Optimal Power Flow
Salvador Pineda, Juan Pérez-Ruiz, Juan Miguel Morales
Power System Optimal Power Flow Power Network Interpretable Learning

June 25, 2024

Large Language Models are Interpretable Learners
Ruochen Wang, Si Si, Felix Yu, Dorothea Wiesmann, Cho-Jui Hsieh, Inderjit Dhillon
Inherent Interpretability Natural Language Description Interpretable Rule Interpretable Learning

February 7, 2024

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks
Peter Graf, Patrick Emami
Inherent Interpretability Data Driven Interpretable Model New Pathway Neurosymbolic AI Policy Network Interpretable Learning Neurosymbolic Programming

January 8, 2024

A Primer on Temporal Graph Learning
Aniq Ur Rahman, Justin P. Coon
Convolutional Neural Network Temporal Graph Learning Spatial Learning Interpretable Learning Learning Architecture

December 11, 2023

Ensemble Interpretation: A Unified Method for Interpretable Machine Learning
Chao Min, Guoyong Liao, Guoquan Wen, Yingjun Li, Xing Guo
Unified Framework Interpretable Machine Learning Multiple View Interpretable Learning Interpretation Method

December 8, 2023

Generative Inverse Design of Metamaterials with Functional Responses by Interpretable Learning
Wei "Wayne" Chen, Rachel Sun, Doksoo Lee, Carlos M. Portela, Wei Chen
Inverse Design Metamaterial Unit Interpretable Learning Generative Inverse Design

November 22, 2023

BackboneLearn: A Library for Scaling Mixed-Integer Optimization-Based Machine Learning
Vassilis Digalakis, Christos Ziakas
Unsupervised Learning Mixed Integer Easy to Use Library Backbone Fine Tuning Interpretable Learning

November 17, 2023

Surprisal Driven $k$-NN for Robust and Interpretable Nonparametric Learning
Amartya Banerjee, Christopher J. Hazard, Jacob Beel, Cade Mack, Jack Xia, Michael Resnick, Will Goddin
Machine Learning Robust Version Nearest Neighbor Non Parametric Learning Conditional Entropy Interpretable Learning Surprisal Driven

September 11, 2023

Interpretable learning of effective dynamics for multiscale systems
Emmanuel Menier, Sebastian Kaltenbach, Mouadh Yagoubi, Marc Schoenauer, Petros Koumoutsakos
Multiscale System Interpretable Learning Effective Dynamic Benchmark Multiscale System

October 17, 2022

A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning
Richard G. Freedman, Joseph B. Mueller, Jack Ladwig, Steven Johnston, David McDonald, Helen Wauck, Ruta Wheelock, Hayley Borck
Complex Reasoning Activity Recognition Visual Sensor Symbolic Representation Interpretable Learning Qualitative Spatial Reasoning Human Posture

May 18, 2022

Automatic Rule Induction for Interpretable Semi-Supervised Learning
Reid Pryzant, Ziyi Yang, Yichong Xu, Chenguang Zhu, Michael Zeng
Semi Supervised Learning Relation Extraction Rule Based Interpretable Learning

February 4, 2022

Learning Interpretable, High-Performing Policies for Autonomous Driving
Rohan Paleja, Yaru Niu, Andrew Silva, Chace Ritchie, Sugju Choi, Matthew Gombolay
Autonomous Driving Autonomous Vehicle Interpretable Policy Interpretable Learning High Performing Policy