Active Learning With Contrastive Explanation

Active learning with contrastive explanation aims to efficiently train machine learning models by strategically selecting the most informative unlabeled data for human annotation, focusing on improving both model accuracy and interpretability. Current research emphasizes integrating explainable AI (XAI) techniques, such as SHAP values and generative models (including GANs, VAEs, and diffusion models), to provide insights into model decisions and guide data selection. This approach is particularly valuable in resource-constrained scenarios and applications requiring high trust and transparency, such as medical image analysis, particle physics simulations, and autonomous driving, where efficient data annotation and model understanding are crucial.

Papers

August 8, 2024

SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios
Sriram Mandalika, Athira Nambiar
Semantic Segmentation Explainable AI Semantic Segmentation Model Active Learning With Contrastive Explanation

July 10, 2024

Applying generative neural networks for fast simulations of the ALICE (CERN) experiment
Maksymilian Wojnar
Generative Adversarial Network Optical Experiment High Energy Physic Generative Neural Network Fast Simulation Calorimeter Simulation Active Learning With Contrastive Explanation Geant4 Simulation

June 5, 2024

May 22, 2024

Particle physics DL-simulation with control over generated data properties
Karol Rogoziński, Jan Dubiński, Przemysław Rokita, Kamil Deja
Raw Data GAN Model External Control Generative Approach Active Learning With Contrastive Explanation

April 13, 2024

ALICE: Combining Feature Selection and Inter-Rater Agreeability for Machine Learning Insights
Bachana Anasashvili, Vahidin Jeleskovic
Machine Learning Inherent Interpretability Feature Selection Churn Prediction Black Box Machine Learning Model Inter Rater Active Learning With Contrastive Explanation

March 26, 2024

Particle identification with machine learning from incomplete data in the ALICE experiment
Maja Karwowska, Łukasz Graczykowski, Kamil Deja, Miłosz Kasak, Małgorzata Janik
Machine Learning New Machine Incomplete Data Active Learning With Contrastive Explanation Particle Identification Particle Picking

December 21, 2023

Machine-learning-based particle identification with missing data
Miłosz Kasak, Kamil Deja, Maja Karwowska, Monika Jakubowska, Łukasz Graczykowski, Małgorzata Janik
Raw Data Active Learning With Contrastive Explanation Particle Identification

October 9, 2023

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners
Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Fang Guo, Qinglin Qi, Jie Zhou, Yue Zhang
Active Learning Line by Line Explanation Active Learning With Contrastive Explanation Low Resource Text Classification Score Based Explanation

September 1, 2023

Explainable Active Learning for Preference Elicitation
Furkan Cantürk, Reyhan Aydoğan
Active Learning Preference Elicitation Active Learning With Contrastive Explanation Limited Labeled Data

August 24, 2023

Human Comprehensible Active Learning of Genome-Scale Metabolic Networks
Lun Ai, Shi-Shun Liang, Wang-Zhou Dai, Liam Hallett, Stephen H. Muggleton, Geoff S. Baldwin
Inductive Logic Programming Active Learning With Contrastive Explanation Metabolic Network

August 7, 2023

Applied metamodelling for ATM performance simulations
Christoffer Riis, Francisco N. Antunes, Tatjana Bolić, Gérald Gurtner, Andrew Cook, Carlos Lima Azevedo, Francisco Câmara Pereira
Model Interpretability Simulation Metamodeling Active Learning With Contrastive Explanation

June 23, 2023

Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN
Jan Dubiński, Kamil Deja, Sandro Wenzel, Przemysław Rokita, Tomasz Trzciński
Machine Learning Generative Model Generative Adversarial Network Variational Autoencoders GAN Architecture Calorimeter Simulation Active Learning With Contrastive Explanation

June 12, 2023

Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation
Ruitao Xie, Jingbang Chen, Limai Jiang, Rui Xiao, Yi Pan, Yunpeng Cai
Generative Adversarial Network Medical Image Explainable Artificial Intelligence Class Specific Feature Class Embeddings Active Learning With Contrastive Explanation

June 18, 2022

A Dynamic Data Driven Approach for Explainable Scene Understanding
Zachary A Daniels, Dimitris Metaxas
Computer Vision Scene Understanding Data Driven Approach Active Learning With Contrastive Explanation Scene Comprehension Vision Based Sensor

Active Learning With Contrastive Explanation

Papers

SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios

Applying generative neural networks for fast simulations of the ALICE (CERN) experiment

Deep Generative Models for Proton Zero Degree Calorimeter Simulations in ALICE, CERN

Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN

Particle physics DL-simulation with control over generated data properties

ALICE: Combining Feature Selection and Inter-Rater Agreeability for Machine Learning Insights

Particle identification with machine learning from incomplete data in the ALICE experiment

Machine-learning-based particle identification with missing data

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners

Explainable Active Learning for Preference Elicitation

Human Comprehensible Active Learning of Genome-Scale Metabolic Networks

Applied metamodelling for ATM performance simulations

Machine Learning methods for simulating particle response in the Zero Degree Calorimeter at the ALICE experiment, CERN

Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation

A Dynamic Data Driven Approach for Explainable Scene Understanding