Interpretable Way

Interpretable AI focuses on developing machine learning models whose decision-making processes are transparent and understandable, addressing the "black box" problem of many deep learning systems. Current research emphasizes creating inherently interpretable models, such as those based on decision trees, rule-based systems, and specific neural network architectures designed for explainability (e.g., concept bottleneck models), as well as developing post-hoc explanation methods like SHAP values. This pursuit of interpretability is crucial for building trust in AI systems, particularly in high-stakes domains like healthcare and finance, and for facilitating better model debugging and validation.

Papers

October 8, 2022

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
Chenliang Zhou, Fangcheng Zhong, Cengiz Oztireli
Image Editing Contrastive Language Image Interpretable Way Feature Augmentation Input Feature Text Guided Image Manipulation Semantic Face

September 30, 2022

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions
Minkyu Kim, Hyun-Soo Choi, Jinho Kim
Black Box Model Interpretable Way Feature Interaction Interpretable Machine Neural Additive Model Interpretable Machine Learning Model

September 26, 2022

Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
Chong Wang, Yuanhong Chen, Yuyuan Liu, Yu Tian, Fengbei Liu, Davis J. McCarthy, Michael Elliott, Helen Frazer, Gustavo Carneiro
Knowledge Distillation Interpretable Way Mammogram Classification Prototype Based Ensemble Weather Multi Prototype Class Agnostic Geometric Prototype

August 28, 2022

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death
Joshua C. Chang, Ted L. Chang, Carson C. Chow, Rohit Mahajan, Sonya Mahajan, Joe Maisog, Shashaank Vattikuti, Hongjing Xia
Interpretable Way Bayesian Deep Learning Survival Model Medical Claim Hospital Readmission Discharge Instruction

August 18, 2022

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables
Adrien Benamira, Tristan Guérand, Thomas Peyrin, Trevor Yap, Bryan Hooi
Convolutional Neural Network Potential Scalability Convolutional Neural Network Model Interpretable Way Differentiable Logic \Mathcal{I}$ Net

August 3, 2022

Interpretable bilinear attention network with domain adaptation improves drug-target prediction
Peizhen Bai, Filip Miljković, Bino John, Haiping Lu
Domain Adaptation Drug Discovery Attention Network Interpretable Way Drug Target Interaction Drug Target Interaction Prediction Drug Target Pair Bilinear Attention

July 3, 2022

Interpretable by Design: Learning Predictors by Composing Interpretable Queries
Aditya Chattopadhyay, Stewart Slocum, Benjamin D. Haeffele, Rene Vidal, Donald Geman
Product Design Interpretable Way Post Hoc Explanation Interpretable Knowledge High Risk Domain

July 1, 2022

Anisotropic, Sparse and Interpretable Physics-Informed Neural Networks for PDEs
Amuthan A. Ramabathiran, Prabhu Ramachandran
Physic Informed Neural Network Many Sparse Partial Differential Equation Interpretable Way Spin Model Localized Sparse Incomplete

June 16, 2022

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering
Zhenyun Deng, Yonghua Zhu, Yang Chen, Michael Witbrock, Patricia Riddle
Interpretable Way Multi Hop Question Answering Question Decomposition Abstract Meaning Representation to Text Interpretable Logical

June 10, 2022

Diffeomorphic Counterfactuals with Generative Models
Ann-Kathrin Dombrowski, Jan E. Gerken, Klaus-Robert Müller, Pan Kessel
Neural Network Generative Model High Quality Counterfactuals Interpretable Way Diffeomorphic Transformation Counterfactual Perturbation

May 31, 2022

GlanceNets: Interpretabile, Leak-proof Concept-based Models
Emanuele Marconato, Andrea Passerini, Stefano Teso
Representation Learning Inherent Interpretability Glance Annotation Interpretable Way High Level Single Learning Concept Based Model

April 17, 2022

Monte Carlo Tree Search for Interpreting Stress in Natural Language
Kyle Swanson, Joy Hsu, Mirac Suzgun
Natural Language Processing Natural Language Monte Carlo Tree Search Interpretable Way Stress Annotation

April 13, 2022

Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
Han Wang, Canwen Xu, Julian McAuley
Language Model Classification Code Interpretable Way Shot Text Classification Label Mapping Prompt Based Pseudo

April 11, 2022

Bayes Point Rule Set Learning
Fabio Aiolli, Luca Bergamin, Tommaso Carraro, Mirko Polato
Inherent Interpretability Interpretable Way Decision Rule Rule Set Probabilistic Rule

March 3, 2022

MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning
Baoquan Zhang, Hao Jiang, Xutao Li, Shanshan Feng, Yunming Ye, Rui Ye
LeArning Abstract Inherent Interpretability Decision Tree Interpretable Way Explainable Decision Class Hierarchy

February 27, 2022

Interpretable Concept-based Prototypical Networks for Few-Shot Learning
Mohammad Reza Zarei, Majid Komeili
LeArning Abstract Fine Grained Shot Learning Interpretable Way Prototypical Network Interpretable Concept Semantic Annotation Black Box Machine Learning Model

January 31, 2022

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
Siqi Miao, Miaoyuan Liu, Pan Li
Graph Attention Interpretable Way Interpretable Graph Task Irrelevant

January 29, 2022

Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer
Yue Wan, Benben Liao, Chang-Yu Hsieh, Shengyu Zhang
Continuum Limit Interpretable Way Retrosynthesis Prediction Cheminformatics Task Chemical Synthesis

January 15, 2022

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
Yuefei Lyu, Xiaoyu Yang, Jiaxin Liu, Philip S. Yu, Sihong Xie, Xi Zhang
Reinforcement Learning Policy OpTimization Interpretable Way Rumor Detection Model Attack Interpretable Policy Effective Reinforcement Learning

December 30, 2021

Causal Attention for Interpretable and Generalizable Graph Classification
Yongduo Sui, Xiang Wang, Jiancan Wu, Min Lin, Xiangnan He, Tat-Seng Chua
Graph Classification Causal Effect Estimation Interpretable Way Causal Feature Causal Attention

Interpretable Way

Papers

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to prevent avoidable all-cause readmissions or death

A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables

Interpretable bilinear attention network with domain adaptation improves drug-target prediction

Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Anisotropic, Sparse and Interpretable Physics-Informed Neural Networks for PDEs

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

Diffeomorphic Counterfactuals with Generative Models

GlanceNets: Interpretabile, Leak-proof Concept-based Models

Monte Carlo Tree Search for Interpreting Stress in Natural Language

Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification

Bayes Point Rule Set Learning

MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning

Interpretable Concept-based Prototypical Networks for Few-Shot Learning

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection

Causal Attention for Interpretable and Generalizable Graph Classification