High Explainability

High explainability in artificial intelligence (AI) aims to make the decision-making processes of complex models, such as large language models and deep neural networks, more transparent and understandable. Current research focuses on developing both intrinsic (built-in) and post-hoc (added after training) explainability methods, often employing techniques like attention mechanisms, feature attribution, and counterfactual examples to interpret model outputs across various modalities (text, images, audio). This pursuit is crucial for building trust in AI systems, particularly in high-stakes domains like medicine and finance, and for ensuring fairness, accountability, and responsible AI development.

Papers

March 24, 2022

Effective Explanations for Entity Resolution Models
Tommaso Teofili, Donatella Firmani, Nick Koudas, Vincenzo Martello, Paolo Merialdo, Divesh Srivastava
High Explainability Counterfactual Explanation Entity Mention Entity Resolution Saliency Explanation Effective Explanation

March 23, 2022

Should Machine Learning Models Report to Us When They Are Clueless?
Roozbeh Yousefzadeh, Xuenan Cao
Machine Learning Model High Explainability Artificial Intelligence Model Shallow Water

March 22, 2022

Explainability in reinforcement learning: perspective and position
Agneza Krajna, Mario Brcic, Tomislav Lipic, Juraj Doncevic
Reinforcement Learning Artificial Intelligence High Explainability Visual Perspective Product Specific Position Information Explainable Reinforcement Learning Artificial Intelligence Method

March 17, 2022

Explainability in Graph Neural Networks: An Experimental Survey
Peibo Li, Yixing Yang, Maurice Pagnucco, Yang Song
Graph Neural Network High Explainability Graph Representation Learning GNN Explanation Experimental Analysis

March 9, 2022

Explainable Machine Learning for Predicting Homicide Clearance in the United States
Gian Maria Campedelli
High Explainability Explainable Machine Learning United State SHAP Score

March 7, 2022

March 6, 2022

Towards a Responsible AI Development Lifecycle: Lessons From Information Security
Erick Galinkin
Inherent Interpretability High Explainability Critical Lesson Security Related Fairness Metric Threat Model

March 2, 2022

March 1, 2022

Explainability for identification of vulnerable groups in machine learning models
Inga Strümke, Marija Slavkovik
Machine Learning Machine Learning Model High Explainability Person Identification Vulnerable Population Machine Learning Fairness

February 24, 2022

Explanatory Paradigms in Neural Networks
Ghassan AlRegib, Mohit Prabhushankar
Neural Network High Explainability Abductive Reasoning Explanatory Paradigm Post Hoc Explainability

February 21, 2022

Explainability in Machine Learning: a Pedagogical Perspective
Andreas Bueff, Ioannis Papantonis, Auste Simkute, Vaishak Belle
Machine Learning High Explainability Pedagogical Alignment Explainability Technique Transparent Machine Learning

February 18, 2022

Explaining, Evaluating and Enhancing Neural Networks' Learned Representations
Marco Bertolini, Djork-Arné Clevert, Floriane Montanari
Neural Network Transfer Learning Representation Learning Inherent Interpretability Line by Line Explanation High Explainability Meaningful Representation Latent Embeddings

February 16, 2022

Explainability of Predictive Process Monitoring Results: Can You See My Data Issues?
Ghada Elkhawaga, Mervat Abuelkheir, Manfred Reichert
Machine Learning Explainable AI High Explainability Process Mining Predictive Process Monitoring Predictive Business Process

February 15, 2022

Explainable Predictive Process Monitoring: A User Evaluation
Williams Rizzi, Marco Comuzzi, Chiara Di Francescomarino, Chiara Ghidini, Suhwan Lee, Fabrizio Maria Maggi, Alexander Nolte
High Explainability Explanation Method User Perception Predictive Process Monitoring Explainable Graph

February 14, 2022

February 10, 2022

High Explainability

Papers

Effective Explanations for Entity Resolution Models

Should Machine Learning Models Report to Us When They Are Clueless?

Explainability in reinforcement learning: perspective and position

Explainability in Graph Neural Networks: An Experimental Survey

Explainable Machine Learning for Predicting Homicide Clearance in the United States

Robustness and Usefulness in AI Explanation Methods

Unsupervised Image Registration Towards Enhancing Performance and Explainability in Cardiac And Brain Image Analysis

Towards a Responsible AI Development Lifecycle: Lessons From Information Security

ADVISE: ADaptive Feature Relevance and VISual Explanations for Convolutional Neural Networks

Satellite Image and Machine Learning based Knowledge Extraction in the Poverty and Welfare Domain

Explainability for identification of vulnerable groups in machine learning models

Explanatory Paradigms in Neural Networks

Explainability in Machine Learning: a Pedagogical Perspective

Explaining, Evaluating and Enhancing Neural Networks' Learned Representations

Explainability of Predictive Process Monitoring Results: Can You See My Data Issues?

Explainable Predictive Process Monitoring: A User Evaluation

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning

Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs

Investigating Explainability of Generative AI for Code through Scenario-based Design