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

April 24, 2024

Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
Dongryeol Lee, Minwoo Lee, Kyungmin Min, Joonsuk Park, Kyomin Jung
Large Language Model Customer Service Interpretable Way Entity Set Expansion QA Model

April 17, 2024

Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning
Simon Tam, Shriram Tallam Puranam Raghu, Étienne Buteau, Erik Scheme, Mounir Boukadoum, Alexandre Campeau-Lecours, Benoit Gosselin
Robust Version Interpretable Way Surface Electromyography Electromyography Signal Metric Based Meta Learning

April 3, 2024

Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models
Matteo Pennisi, Giovanni Bellitto, Simone Palazzo, Mubarak Shah, Concetto Spampinato
Diffusion Model Interpretable Way Cross Modality Transfer Language Vision Model Multi Modal Explanation

March 25, 2024

An Incremental MaxSAT-based Model to Learn Interpretable and Balanced Classification Rules
Antônio Carlos Souza Ferreira Júnior, Thiago Alves Rocha
Machine Learning Inherent Interpretability Interpretable Model Interpretable Way MaxSAT Solver Classification Rule Balanced Classification

March 19, 2024

Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
Filip Ilic, He Zhao, Thomas Pock, Richard P. Wildes
Action Recognition Privacy Preserving Interpretable Way Obfuscation Technique Selective Engagement

March 14, 2024

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
Nicholas Zolman, Urban Fasel, J. Nathan Kutz, Steven L. Brunton
Deep Reinforcement Learning Nonlinear Dynamic Interpretable Way Neural Network Policy Weak Sindy Interpretable Control

February 29, 2024

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
Zhiyu An, Xianzhong Ding, Wan Du
Product Design Model Based Reinforcement Learning Black Box Model Interpretable Way Learning Agent Policy Adaptation Heating, Ventilation, and Air Conditioning

February 19, 2024

January 5, 2024

Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery
Daniel Waxman, Kurt Butler, Petar M. Djuric
Interpretable Way Differentiable Model Causal Strength Differentiable Causal Discovery

December 29, 2023

Interpretable and Explainable Machine Learning Methods for Predictive Process Monitoring: A Systematic Literature Review
Nijat Mehdiyev, Maxim Majlatow, Peter Fettke
Machine Learning Inherent Interpretability Interpretable Model Systematic Literature Review Process Mining Interpretable Way Predictive Process Monitoring Predictive Process

November 30, 2023

Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Chong Wang, Yuanhong Chen, Fengbei Liu, Yuyuan Liu, Davis James McCarthy, Helen Frazer, Gustavo Carneiro
Generative Model Mixture Component Interpretable Way Latent Prototype Interpretable Image Prototype Selection Prototype Quality Specific Prototype

November 20, 2023

An NMF-Based Building Block for Interpretable Neural Networks With Continual Learning
Brian K. Vogel
Continual LEArning Inherent Interpretability Recurrent Neural Network Interpretable Way Non Negative Matrix Factorization Interpretable Neural Network Negative Matrix Factorization

November 15, 2023

Interpretable by Design: Wrapper Boxes Combine Neural Performance with Faithful Explanations
Yiheng Su, Juni Jessy Li, Matthew Lease
Product Design Interpretable Model Neural Model Interpretable Way Faithful Explanation

October 28, 2023

Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning
Ammar N. Abbas, Georgios C. Chasparis, John D. Kelleher
Reinforcement Learning Deep Reinforcement Learning Policy Learning Interpretable Way Complex System Hierarchical Framework Safety Critical System Model Based Safe Reinforcement Learning

October 23, 2023

Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number
Sophie Hao, Tal Linzen
Transformer Megatron Decepticons Meaningful Representation Interpretable Way Data Encoding Early Slavic Participle Translation Accuracy Linear Code

October 19, 2023

MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale
Haitian Jiang, Renjie Liu, Xiao Yan, Zhenkun Cai, Minjie Wang, David Wipf
Graph Neural Network Visual Analogue Scale Node Embeddings Interpretable Way Scalable Graph Neural Network

October 11, 2023

NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations
Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee
Deep Learning Counterfactual Explanation Interpretable Way Code Debugging

September 23, 2023

Interpretable and Flexible Target-Conditioned Neural Planners For Autonomous Vehicles
Haolan Liu, Jishen Zhao, Liangjun Zhang
Autonomous Vehicle Collision Avoidance Extension Study Interpretable Way Neural Planner Driving Planning

Interpretable Way

Papers

Return of EM: Entity-driven Answer Set Expansion for QA Evaluation

Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning

Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models

An Incremental MaxSAT-based Model to Learn Interpretable and Balanced Classification Rules

Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control

SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding

Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks

Interpretable Embedding for Ad-hoc Video Search

Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery

Interpretable and Explainable Machine Learning Methods for Predictive Process Monitoring: A Systematic Literature Review

Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition

An NMF-Based Building Block for Interpretable Neural Networks With Continual Learning

Interpretable by Design: Wrapper Boxes Combine Neural Performance with Faithful Explanations

Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning

Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number

MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale

NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations

Interpretable and Flexible Target-Conditioned Neural Planners For Autonomous Vehicles