Inherent Interpretability

Inherent interpretability in machine learning focuses on designing models and methods that are inherently transparent and understandable, aiming to reduce the "black box" nature of many AI systems. Current research emphasizes developing intrinsically interpretable model architectures, such as those based on decision trees, rule-based systems, and specific neural network designs (e.g., Kolmogorov-Arnold Networks), alongside techniques like feature attribution and visualization methods to enhance understanding of model behavior. This pursuit is crucial for building trust in AI, particularly in high-stakes applications like healthcare and finance, where understanding model decisions is paramount for responsible deployment and effective human-AI collaboration.

Papers

August 17, 2022

A Concept and Argumentation based Interpretable Model in High Risk Domains
Haixiao Chi, Dawei Wang, Gaojie Cui, Feng Mao, Beishui Liao
Inherent Interpretability Interpretable Model High Impact Concept Spoken Argumentation Concept Based Explanation High Risk Domain Quantitative Argumentation

August 12, 2022

Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis
Zhiyu Jin, Xuli Shen, Bin Li, Xiangyang Xue
Inherent Interpretability Style Transfer Controllability Condition Fourier Analysis Reconstruction Loss

August 11, 2022

RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data
Thibaud Godon, Pier-Luc Plante, Baptiste Bauvin, Elina Francovic-Fontaine, Alexandre Drouin, Jacques Corbeil
Inherent Interpretability Ensemble Learning Interpretable Model Metabolomics Data Sparse Classification Interpretable Ensemble

August 5, 2022

Explanation of Machine Learning Models of Colon Cancer Using SHAP Considering Interaction Effects
Yasunobu Nohara, Toyoshi Inoguchi, Chinatsu Nojiri, Naoki Nakashima
Machine Learning Model Inherent Interpretability Line by Line Explanation Colorectal Cancer Shapley Additive Explanation Shapley Interaction Interaction Effect

July 28, 2022

An Interpretability Evaluation Benchmark for Pre-trained Language Models
Yaozong Shen, Lijie Wang, Ying Chen, Xinyan Xiao, Jing Liu, Hua Wu
Pre Trained Language Model Inherent Interpretability Syntax Aware Word Prediction

July 26, 2022

From Interpretable Filters to Predictions of Convolutional Neural Networks with Explainable Artificial Intelligence
Shagufta Henna, Juan Miguel Lopez Alcaraz
Convolutional Neural Network Human Prediction Inherent Interpretability Explainable Artificial Intelligence CNN Network Convolutional Neural Network Model Convolutional Filter

July 23, 2022

A general-purpose method for applying Explainable AI for Anomaly Detection
John Sipple, Abdou Youssef
Anomaly Detection Inherent Interpretability Explainable AI High Explainability Unsupervised Anomaly Detection Inferior Attribution Performance

July 20, 2022

Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation
Ricardo Bigolin Lanfredi, Joyce D. Schroeder, Tolga Tasdizen
Convolutional Neural Network Inherent Interpretability Chest X Ray Bounding Box Gaze Annotation Supervised Localization

July 11, 2022

July 8, 2022

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective
Sejin Seo, Jihong Park, Seung-Woo Ko, Jinho Choi, Mehdi Bennis, Seong-Lyun Kim
Inherent Interpretability Semantic Communication Probabilistic Logic Interpretable Graph Medium Access Control Protocol Design

July 6, 2022

Boosting the interpretability of clinical risk scores with intervention predictions
Eric Loreaux, Ke Yu, Jonas Kemp, Martin Seneviratne, Christina Chen, Subhrajit Roy, Ivan Protsyuk, Natalie Harris, Alexander D'Amour, Steve Yadlowsky, Ming-Jun Chen
Inherent Interpretability Intensive Care Unit Intervention Policy Adverse Drug Event

July 5, 2022

Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications
Thomas Hickling, Abdelhafid Zenati, Nabil Aouf, Phillippa Spencer
Deep Reinforcement Learning Financial Application Inherent Interpretability Narrative Review High Explainability Explainable Artificial Intelligence Current Method

July 4, 2022

July 2, 2022

A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data
Magdalena Wysocka, Oskar Wysocki, Marie Zufferey, Dónal Landers, André Freitas
Inherent Interpretability Systematic Review Cancer Diagnosis Human Interpretability Cancer Registry

June 30, 2022

Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
Zijie J. Wang, Alex Kale, Harsha Nori, Peter Stella, Mark E. Nunnally, Duen Horng Chau, Mihaela Vorvoreanu, Jennifer Wortman Vaughan, Rich Caruana
Machine Learning Machine Learning Model Inherent Interpretability Interpretability Method Policy Value

June 29, 2022

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks
Venelin Kovatchev, Trina Chatterjee, Venkata S Govindarajan, Jifan Chen, Eunsol Choi, Gabriella Chronis, Anubrata Das, Katrin Erk, Matthew Lease, Junyi Jessy Li, Yating Wu, Kyle Mahowald
Adversarial Attack Inherent Interpretability Question Answering Model Historical Linguistics Systematic Approach Adversarial Data Collection Adversarial Question Error Prediction

June 28, 2022

Explaining Any ML Model? -- On Goals and Capabilities of XAI
Moritz Renftle, Holger Trittenbach, Michael Poznic, Reinhard Heil
Machine Learning Model Inherent Interpretability High Explainability XAI Method xAI Community Capability Evolution eXplainable Artificial Intelligence Pseudo Goal

June 24, 2022

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Zulqarnain Khan, Davin Hill, Aria Masoomi, Joshua Bone, Jennifer Dy
Native Robustness Inherent Interpretability Robust Explanation Local Prediction Prediction Function

Inherent Interpretability

Papers

A Concept and Argumentation based Interpretable Model in High Risk Domains

Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis

RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data

Explanation of Machine Learning Models of Colon Cancer Using SHAP Considering Interaction Effects

An Interpretability Evaluation Benchmark for Pre-trained Language Models

From Interpretable Filters to Predictions of Convolutional Neural Networks with Explainable Artificial Intelligence

A general-purpose method for applying Explainable AI for Anomaly Detection

Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation

Interpretability by design using computer vision for behavioral sensing in child and adolescent psychiatry

A multi-level interpretable sleep stage scoring system by infusing experts' knowledge into a deep network architecture

Towards Semantic Communication Protocols: A Probabilistic Logic Perspective

Boosting the interpretability of clinical risk scores with intervention predictions

Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications

Generalisable Methods for Early Prediction in Interactive Simulations for Education

Comparing Feature Importance and Rule Extraction for Interpretability on Text Data

A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data

Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks

Explaining Any ML Model? -- On Goals and Capabilities of XAI

Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions