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

November 18, 2024

ST-Tree with Interpretability for Multivariate Time Series Classification
Mingsen Du, Yanxuan Wei, Yingxia Tang, Xiangwei Zheng, Shoushui Wei, Cun Ji
Classification Code Inherent Interpretability Multivariate Time Series Swin Transformer Multivariate Time Series Classification Tree Transformer Neural Tree

November 15, 2024

Fill in the blanks: Rethinking Interpretability in vision
Pathirage N. Deelaka, Tharindu Wickremasinghe, Devin Y. De Silva, Lisara N. Gajaweera
Inherent Interpretability Explainable AI Vision Paper Model Interpretability Model Agnostic Explainability

November 14, 2024

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems
Benjamin Kolicic, Alberto Caron, Chris Hicks, Vasilios Mavroudis
LeArning Abstract Inherent Interpretability Uncertainty Quantification Online Service Security Implication Uncertainty Aware Model Uncertainty Awareness

November 12, 2024

Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
Eleonora Mancini, Francesco Paissan, Paolo Torroni, Cem Subakan, Mirco Ravanelli
Data Detection Inherent Interpretability Speech Analysis Parkinson Disease Explainability Method Interpretability Method Speech Feature Parkinson'S Disease

November 10, 2024

CineXDrama: Relevance Detection and Sentiment Analysis of Bangla YouTube Comments on Movie-Drama using Transformers: Insights from Interpretability Tool
Usafa Akther Rifa, Pronay Debnath, Busra Kamal Rafa, Shamaun Safa Hridi, Md. Aminur Rahman
Inherent Interpretability Sentiment Analysis Implicit Sentiment User Sentiment Bangla Text Relative Relevance Relevance Modeling Movie Dataset

November 8, 2024

November 7, 2024

November 6, 2024

November 5, 2024

SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features
Zhuoshuo Li (1), Jiong Zhang (2), Youbing Zeng (1), Jiaying Lin (1), Dan Zhang (3), Jianjia Zhang (1), Duan Xu (4), Hosung Kim (5), Bingguang Liu (6), Mengting Liu (1) ((1) Department of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China, (2) Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China, (3) School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China, (4) Department of Radiology, School of Medicine, University of California San Francisco, San Francisco, CA, USA, (5) USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA, (6) Department of Radiology, Shenzhen Maternity and Child Healthcare Hospital, Shenzhen, China)
Inherent Interpretability Predictive Model Brain Age Activation Map Cortical Surface Interpretable Graph Neural Network

November 4, 2024

Do graph neural network states contain graph properties?
Tom Pelletreau-Duris, Ruud van Bakel, Michael Cochez
Graph Neural Network Graph Drawing Inherent Interpretability Graph Feature Graph Learning Model Neural State Model Agnostic Explainability

October 30, 2024

MIXAD: Memory-Induced Explainable Time Series Anomaly Detection
Minha Kim, Kishor Kumar Bhaumik, Amin Ahsan Ali, Simon S. Woo
Anomaly Detection Inherent Interpretability Multivariate Time Series Data Interpretability Evaluation

October 28, 2024

October 27, 2024

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
Qi Zhang, Yifei Wang, Jingyi Cui, Xiang Pan, Qi Lei, Stefanie Jegelka, Yisen Wang
Native Robustness Full Model Inherent Interpretability Big Gain Polysemous Word Revisit Monosemanticity

Inherent Interpretability

Papers

ST-Tree with Interpretability for Multivariate Time Series Classification

Fill in the blanks: Rethinking Interpretability in vision

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems

Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Enhancing Phishing Detection through Feature Importance Analysis and Explainable AI: A Comparative Study of CatBoost, XGBoost, and EBM Models

CineXDrama: Relevance Detection and Sentiment Analysis of Bangla YouTube Comments on Movie-Drama using Transformers: Insights from Interpretability Tool

A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis

Decoding Report Generators: A Cyclic Vision-Language Adapter for Counterfactual Explanations

Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review

Explainable AI through a Democratic Lens: DhondtXAI for Proportional Feature Importance Using the D'Hondt Method

Towards Unifying Interpretability and Control: Evaluation via Intervention

Local vs distributed representations: What is the right basis for interpretability?

Human-in-the-Loop Feature Selection Using Interpretable Kolmogorov-Arnold Network-based Double Deep Q-Network

SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical features

Do graph neural network states contain graph properties?

MIXAD: Memory-Induced Explainable Time Series Anomaly Detection

Deep Trees for (Un)structured Data: Tractability, Performance, and Interpretability

Towards Multi-dimensional Explanation Alignment for Medical Classification

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness