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

October 24, 2023

Interpretable Medical Image Classification using Prototype Learning and Privileged Information
Luisa Gallee, Meinrad Beer, Michael Goetz
Inherent Interpretability Capsule Network Privileged Information Baseline Model Radiologist Annotation Prototype Representation

October 23, 2023

October 20, 2023

Explainable Depression Symptom Detection in Social Media
Eliseo Bao Souto, Anxo Pérez, Javier Parapar
Inherent Interpretability Social Medium Mental Health Depression Symptom Symptom Based

October 19, 2023

October 18, 2023

October 13, 2023

A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check
Haojing Huang, Jingheng Ye, Qingyu Zhou, Yinghui Li, Yangning Li, Feng Zhou, Hai-Tao Zheng
Inherent Interpretability Plug and Play Dynamic ModulE Chinese Spelling Reasoning Module

October 11, 2023

Human-Centered Evaluation of XAI Methods
Karam Dawoud, Wojciech Samek, Peter Eisert, Sebastian Lapuschkin, Sebastian Bosse
Deep Learning Inherent Interpretability Image Classification XAI Method Layer Wise Relevance Propagation Human Centered Evaluation

October 10, 2023

October 9, 2023

Enhancing Interpretability and Generalizability in Extended Isolation Forests
Alessio Arcudi, Davide Frizzo, Chiara Masiero, Gian Antonio Susto
Anomaly Detection Inherent Interpretability Unsupervised Setting Isolation Forest Interpretability Tool Improved Generalizability

October 6, 2023

October 5, 2023

Learning Personalized Alignment for Evaluating Open-ended Text Generation
Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian
Large Language Model Inherent Interpretability Human Preference Story Generation Open Ended Text Generation Personalized Alignment

October 4, 2023

Stable and Interpretable Deep Learning for Tabular Data: Introducing InterpreTabNet with the Novel InterpreStability Metric
Shiyun Wa, Xinai Lu, Minjuan Wang
Inherent Interpretability Tabular Data Explainable Model Interpretable Deep Learning Interpretable AI Sensor Interoperability

October 2, 2023

A Framework for Interpretability in Machine Learning for Medical Imaging
Alan Q. Wang, Batuhan K. Karaman, Heejong Kim, Jacob Rosenthal, Rachit Saluja, Sean I. Young, Mert R. Sabuncu
Machine Learning Machine Learning Model New Framework Inherent Interpretability Medical Image Analysis Medical Imaging Interpretability Research Model Transparency

Inherent Interpretability

Papers

Interpretable Medical Image Classification using Prototype Learning and Privileged Information

Machine Learning and Knowledge: Why Robustness Matters

Efficient and Interpretable Bandit Algorithms

Explainable Depression Symptom Detection in Social Media

Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks

Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models

Understanding Video Transformers for Segmentation: A Survey of Application and Interpretability

A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering

A Uniform Language to Explain Decision Trees

A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check

Human-Centered Evaluation of XAI Methods

Neural Harmonium: An Interpretable Deep Structure for Nonlinear Dynamic System Identification with Application to Audio Processing

On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis

Enhancing Interpretability and Generalizability in Extended Isolation Forests

SPADE: Sparsity-Guided Debugging for Deep Neural Networks

Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates

Learning Personalized Alignment for Evaluating Open-ended Text Generation

Stable and Interpretable Deep Learning for Tabular Data: Introducing InterpreTabNet with the Novel InterpreStability Metric

A Framework for Interpretability in Machine Learning for Medical Imaging