Self Interpretable Model

Self-interpretable models aim to create machine learning systems that are both accurate in their predictions and transparent in their decision-making processes, addressing the "black box" problem of many deep learning models. Current research focuses on developing novel architectures and algorithms, such as rule-based systems, neural pattern associators, and tree-based structures, that inherently provide understandable explanations alongside predictions. This work is significant because it enhances trust and allows for better understanding and debugging of AI systems, particularly in high-stakes applications like healthcare and autonomous systems where explainability is crucial. The development of self-interpretable models is driving progress towards more reliable and responsible AI.

Papers

October 29, 2024

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models
Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang, Xuyang Liu, Weiya Li, Xuming Hu, Linfeng Zhang
Full Model Explainable AI Black Box Black Box Model Self Interpretable Model Self Interpretable

June 2, 2024

DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
Yinjun Wu, Mayank Keoliya, Kan Chen, Neelay Velingker, Ziyang Li, Emily J Getzen, Qi Long, Mayur Naik, Ravi B Parikh, Eric Wong
Treatment Effect Data Discretization Faithful Explanation Rule Based Explanation Treatment Effect Estimation Self Interpretable Model

January 25, 2024

Within-basket Recommendation via Neural Pattern Associator
Kai Luo, Tianshu Shen, Lan Yao, Ga Wu, Aaron Liblong, Istvan Fehervari, Ruijian An, Jawad Ahmed, Harshit Mishra, Charu Pujari
Associative Recall Deep Association Self Interpretable Model Shopping Intent Basket Recommendation

January 14, 2024

BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions
Xiao Liu, Jie Zhao, Wubing Chen, Mao Tan, Yongxing Su
Deep Reinforcement Learning Multi Agent Self Interpretable Model Interpretable Structure

October 30, 2023

LILO: Learning Interpretable Libraries by Compressing and Documenting Code
Gabriel Grand, Lionel Wong, Maddy Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas
Large Language Model Code Generation Program Synthesis Code Corpus Program Synthesis Benchmark Self Interpretable Model

September 14, 2023

Interpretability-Aware Vision Transformer
Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Vision Transformer Inherent Interpretability Model Interpretability Self Interpretable Model

May 31, 2023

EAMDrift: An interpretable self retrain model for time series
Gonçalo Mateus, Cláudia Soares, João Leitão, António Rodrigues
Human Prediction Time Series Time Series Forecasting Time Series Prediction Self Interpretable Model

March 13, 2023

A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers
Sourya Sengupta, Mark A. Anastasio
Inherent Interpretability Binary Classifier Estimation Method Self Interpretable Model Test Statistic Self Interpretable

March 6, 2023

A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
Xiang Hu, Xinyu Kong, Kewei Tu
Text Classification Neuro Symbolic Sentence Level Single Label Multi Label Text Classification Self Interpretable Model

November 9, 2021

Self-Interpretable Model with TransformationEquivariant Interpretation
Yipei Wang, Xiaoqian Wang
Robust Interpretation Self Interpretable Model