Interpretable Prediction

Interpretable prediction focuses on developing machine learning models that not only achieve high predictive accuracy but also provide understandable explanations for their decisions. Current research emphasizes developing novel model architectures, such as rule-set models, variational autoencoders, and neural-symbolic approaches, that inherently incorporate interpretability or generate easily understandable explanations alongside predictions. This field is crucial for building trust in AI systems, particularly in high-stakes domains like healthcare and finance, where understanding the reasoning behind predictions is paramount for responsible decision-making.

Papers

August 11, 2024

PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data Settings
Vaibhav Ganatra, Drishti Goel
Deep Learning Model Medical Image Datasets Visual Prototype Explainable Classification Group Imbalance Interpretable by Design Scarce Data Interpretable Prediction Medical Image Classification Task

June 5, 2024

Efficient Exploration of the Rashomon Set of Rule Set Models
Martino Ciaperoni, Han Xiao, Aristides Gionis
Efficient Exploration Interpretable Machine Learning Interpretable Prediction Rule Set Rashomon Set Complex Predictive Model Rule Model

May 21, 2024

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis
Sandra Zilker, Sven Weinzierl, Mathias Kraus, Patrick Zschech, Martin Matzner
Patient Friendly Language Outcome Prediction Clinical Decision Support Patient Trajectory Standard Sepsis Interpretable Prediction Patient Pathway

May 16, 2024

The fast committor machine: Interpretable prediction with kernels
D. Aristoff, M. Johnson, G. Simpson, R. J. Webber
Small Kernel Kernel Based Stochastic System Interpretable Prediction Committor Function

April 23, 2024

Interpretable Prediction and Feature Selection for Survival Analysis
Mike Van Ness, Madeleine Udell
Feature Selection Survival Model Survival Analysis Survival Datasets Interpretable Prediction

November 9, 2023

Deep Natural Language Feature Learning for Interpretable Prediction
Felipe Urrutia, Cristian Buc, Valentin Barriere
Natural Language Natural Language Inference Linguistic Representation Word Model Interpretable Prediction

August 24, 2023

Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions
Kwan Ho Ryan Chan, Aditya Chattopadhyay, Benjamin David Haeffele, Rene Vidal
Multimodal Model Large Language Concept Bottleneck Model Interpretable Concept Built in Interpretability Interpretable Prediction Sparse Variational Concept Filtering

May 25, 2023

Explainability Techniques for Chemical Language Models
Stefan Hödl, William Robinson, Yoram Bachrach, Wilhelm Huck, Tal Kachman
Self Attention Chemical Data Chemical Language Model Explainability Technique Interpretable Prediction Molecular String Representation

February 6, 2023

Variational Information Pursuit for Interpretable Predictions
Aditya Chattopadhyay, Kwan Ho Ryan Chan, Benjamin D. Haeffele, Donald Geman, René Vidal
Generative Model Generative Modeling Interpretable Prediction Information Acquisition Sparse Variational Interpretable Knowledge

December 21, 2022

End-to-end AI framework for interpretable prediction of molecular and crystal properties
Hyun Park, Ruijie Zhu, E. A. Huerta, Santanu Chaudhuri, Emad Tajkhorshid, Donny Cooper
Hyperparameter Optimization Computational Approach Flexible Framework Crystal Property Interpretable Prediction Artificial Intelligence Framework Driven Scientific Discovery

December 6, 2022

Explainability as statistical inference
Hugo Henri Joseph Senetaire, Damien Garreau, Jes Frellsen, Pierre-Alexandre Mattei
Inherent Interpretability High Explainability Interpretability Method Statistical Inference Deep Probabilistic Model Interpretable Prediction

October 31, 2022

Uncertainty Aware Trader-Company Method: Interpretable Stock Price Prediction Capturing Uncertainty
Yugo Fujimoto, Kei Nakagawa, Kentaro Imajo, Kentaro Minami
Predictive Performance Stock Price Forecasting Predictive Power Interpretable Prediction Uncertainty Awareness

September 26, 2022

Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification
Adrien Bennetot, Gianni Franchi, Javier Del Ser, Raja Chatila, Natalia Diaz-Rodriguez
Deep Learning Model Image Classification Explainable AI Opaque Machine Learning Model Transparency Interpretable Prediction Explainable Predictive Neural Symbolic Learning

April 1, 2022

Provable concept learning for interpretable predictions using variational autoencoders
Armeen Taeb, Nicolo Ruggeri, Carina Schnuck, Fanny Yang
Ground Truth Variational Autoencoders Interpretable Concept Interpretable Prediction

March 24, 2022

Interpretable Prediction of Pulmonary Hypertension in Newborns using Echocardiograms
Hanna Ragnarsdottir, Laura Manduchi, Holger Michel, Fabian Laumer, Sven Wellmann, Ece Ozkan, Julia Vogt
Severity Prediction Transesophageal Echocardiography Interpretable Prediction Pulmonary Hypertension Echocardiogram Interpretation Cardiac Anatomy Newborn Level Performance

March 23, 2022

Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning
Weicheng Zhu, Carlos Fernandez-Granda, Narges Razavian
Self Supervised Learning Interpretable Prediction Recurrence Prediction H&E Stained

February 2, 2022

MPVNN: Mutated Pathway Visible Neural Network Architecture for Interpretable Prediction of Cancer-specific Survival Risk
Gourab Ghosh Roy, Nicholas Geard, Karin Verspoor, Shan He
Survival Prediction Biological Pathway Outcome Prediction Survival Analysis Interpretable Prediction

Interpretable Prediction

Papers

PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data Settings

Efficient Exploration of the Rashomon Set of Rule Set Models

A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis

The fast committor machine: Interpretable prediction with kernels

Interpretable Prediction and Feature Selection for Survival Analysis

Deep Natural Language Feature Learning for Interpretable Prediction

Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions

Explainability Techniques for Chemical Language Models

Variational Information Pursuit for Interpretable Predictions

End-to-end AI framework for interpretable prediction of molecular and crystal properties

Explainability as statistical inference

Uncertainty Aware Trader-Company Method: Interpretable Stock Price Prediction Capturing Uncertainty

Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification

Provable concept learning for interpretable predictions using variational autoencoders

Interpretable Prediction of Pulmonary Hypertension in Newborns using Echocardiograms

Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning

MPVNN: Mutated Pathway Visible Neural Network Architecture for Interpretable Prediction of Cancer-specific Survival Risk