BenchXAI: Comprehensive Benchmarking of Post-hoc Explainable AI Methods on Multi-Modal Biomedical Data DOI Creative Commons
Jacqueline Michelle Metsch, Anne-Christin Hauschild

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Abstract The increasing digitalisation of multi-modal data in medicine and novel artificial intelligence (AI) algorithms opens up a large number opportunities for predictive models. In particular, deep learning models show great performance the medical field. A major limitation such powerful but complex originates from their ’black-box’ nature. Recently, variety explainable AI (XAI) methods have been introduced to address this lack transparency trust AI. However, majority solely evaluated on single modalities. Meanwhile, with XAI methods, integrative frameworks benchmarks are essential compare different tasks. For that reason, we developed BenchXAI, benchmarking package supporting comprehensive evaluation fifteen investigating robustness, suitability, limitations biomedical data. We employed BenchXAI validate these three common tasks, namely clinical data, image signal biomolecular Our newly designed sample-wise normalisation approach post-hoc enables statistical visualisation robustness. found Integrated Gradients, DeepLift, DeepLiftShap, GradientShap performed well over all while like Deconvolution, Guided Backpropagation, LRP- α 1- β 0 struggled some With acts as EU Act application domain becomes more essential. study represents first step toward verifying suitability various domains.

Language: Английский

On the disagreement problem in Human-in-the-Loop federated machine learning DOI Creative Commons

Matthias J. M. Huelser,

Heimo Mueller,

Natalia Díaz-Rodríguez

et al.

Journal of Industrial Information Integration, Journal Year: 2025, Volume and Issue: unknown, P. 100827 - 100827

Published: March 1, 2025

Language: Английский

Citations

0

Attention Learning with Counterfactual Intervention based on Feature Fusion for Fine-grained Feature Learning DOI
Ning Yu,

Long Chen,

Xiaoyin Yi

et al.

Digital Signal Processing, Journal Year: 2025, Volume and Issue: unknown, P. 105215 - 105215

Published: April 1, 2025

Language: Английский

Citations

0

Protocol for implementing the nested model for AI design and validation in compliance with AI regulations DOI
Akshat Dubey, Zewen Yang, Aleksandar Anžel

et al.

STAR Protocols, Journal Year: 2025, Volume and Issue: 6(2), P. 103771 - 103771

Published: April 11, 2025

Language: Английский

Citations

0

Explainable and context-aware Graph Neural Networks for dynamic electric vehicle route optimization to optimal charging station DOI
Shalini Kapoor

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127331 - 127331

Published: April 1, 2025

Language: Английский

Citations

0

IRAF-BRB: An Explainable AI Framework for Enhanced Interpretability in Project Risk Assessment DOI Creative Commons
Bodrunnessa Badhon, Ripon K. Chakrabortty, Sreenatha G. Anavatti

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127979 - 127979

Published: May 1, 2025

Language: Английский

Citations

0

Puzzle mode graph learning with pattern composition relationships reasoning for defect detection of printed products DOI
Zixun Zhu, Jie Zhang, Junliang Wang

et al.

Journal of Manufacturing Systems, Journal Year: 2025, Volume and Issue: 81, P. 34 - 48

Published: May 17, 2025

Language: Английский

Citations

0

Exploring Causal Learning Through Graph Neural Networks: An In‐Depth Review DOI Creative Commons
Simi Job, Xiaohui Tao, Taotao Cai

et al.

Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, Journal Year: 2025, Volume and Issue: 15(2)

Published: May 19, 2025

ABSTRACT In machine learning, exploring data correlations to predict outcomes is a fundamental task. Recognizing causal relationships embedded within pivotal for comprehensive understanding of system dynamics, the significance which paramount in data‐driven decision‐making processes. Beyond traditional methods, there has been shift toward using graph neural networks (GNNs) given their capabilities as universal approximators. Thus, thorough review advancements learning GNNs both relevant and timely. To structure this review, we introduce novel taxonomy that encompasses various state‐of‐the‐art GNN methods used studying causality. are further categorized based on applications causality domain. We provide an exhaustive compilation datasets integral with serve resource practical study. This also touches upon application across diverse sectors. conclude insights into potential challenges promising avenues future exploration rapidly evolving field learning.

Language: Английский

Citations

0

Agent-in-the-Loop to Distill Expert Knowledge into Artificial Intelligence Models: A Survey DOI

Jiayuan Gao,

Yingwei Zhang, Yiqiang Chen

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 8, 2025

Abstract Large-scale neural networks have revolutionized many general knowledge areas (e.g., computer vision and language processing), but are still rarely applied in expert healthcare), due to data sparsity high annotation expenses. Human-in-the-loop machine learning (HIL-ML) incorporates domain into the modeling process, effectively addressing these challenges.Recently, some researchers started using large models substitute for certain tasks typically performed by humans. Although limitations areas, after being trained on trillions of examples, they demonstrated advanced capabilities reasoning, semantic understanding, grounding, planning. These can serve as proxies human, which introduces new opportunities challenges HIL-ML area.Based above, we summarize a more comprehensive framework, Agent-in-the-Loop Machine Learning (AIL-ML), where agent represents both humans models. AIL-ML efficiently collaborate human model construct vertical AI with lower costs.This paper presents first review recent advancements this area. First, provide formal definition discuss its related fields. Then, categorize methods based processing development, providing definitions each, present representative works detail each category. Third, highlight relative applications AIL-ML. Finally, current literature future research directions.

Language: Английский

Citations

0

BenchXAI: Comprehensive benchmarking of post-hoc explainable AI methods on multi-modal biomedical data DOI Creative Commons
Jacqueline Michelle Metsch, Anne-Christin Hauschild

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 191, P. 110124 - 110124

Published: April 15, 2025

The increasing digitalization of multi-modal data in medicine and novel artificial intelligence (AI) algorithms opens up a large number opportunities for predictive models. In particular, deep learning models show great performance the medical field. A major limitation such powerful but complex originates from their 'black-box' nature. Recently, variety explainable AI (XAI) methods have been introduced to address this lack transparency trust AI. However, majority solely evaluated on single modalities. Meanwhile, with XAI methods, integrative frameworks benchmarks are essential compare different tasks. For that reason, we developed BenchXAI, benchmarking package supporting comprehensive evaluation fifteen investigating robustness, suitability, limitations biomedical data. We employed BenchXAI validate these three common tasks, namely clinical data, image signal biomolecular Our newly designed sample-wise normalization approach post-hoc enables statistical visualization robustness. found Integrated Gradients, DeepLift, DeepLiftShap, GradientShap performed well over all while like Deconvolution, Guided Backpropagation, LRP-α1-β0 struggled some With acts as EU Act application domain becomes more essential. study represents first step towards verifying suitability various domains.

Language: Английский

Citations

0

TELL-ME: Toward Personalized Explanations of Large Language Models DOI

Jakub Jeck,

Florian Leiser,

Anne Hüsges

et al.

Published: April 23, 2025

Language: Английский

Citations

0