Explainable AI: XAI-Guided Context-Aware Data Augmentation

📅 2025-05-01
🏛️ Expert systems with applications
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the scarcity of labeled data for low-resource languages and the limitations of existing data augmentation methods—including noise injection, semantic drift, and disruption of contextual coherence—this paper proposes an XAI-driven, context-aware data augmentation framework. The method introduces a novel attribution-aligned augmentation strategy selection mechanism, leveraging Grad-CAM and SHAP interpretability feedback to guide contrastive learning–informed conditional GANs in generating decision-relevant, semantically faithful synthetic samples. Additionally, domain-knowledge-enhanced semantic similarity constraints are incorporated to preserve contextual consistency and task relevance during perturbation. Evaluated on ImageNet-1K and CheXpert, the framework improves ResNet-50’s average top-1 accuracy by 2.3%. It also significantly enhances model interpretability, increasing Faithfulness by 31% and Plausibility by 27%. To our knowledge, this is the first approach to achieve dynamic co-optimization of data augmentation and model attribution.

Technology Category

Application Category

Problem

Research questions and friction points this paper is trying to address.

Addressing labeled data scarcity in low-resource languages
Reducing noise and semantic drift in data augmentation
Enhancing model accuracy with XAI-guided augmentation
Innovation

Methods, ideas, or system contributions that make the work stand out.

XAI-Guided Context-Aware Data Augmentation framework
Modifies less critical features selectively
Iterative feedback loop refines augmented data
🔎 Similar Papers
No similar papers found.
Melkamu Abay Mersha
Melkamu Abay Mersha
PhD Candidate, University of Colorado Colorado Springs
AIMachine learningXAINLP
M
M. Yigezu
Instituto Politécnico Nacional (IPN), Centro de Investigación en Computación (CIC), 07738, Mexico City, Mexico
A
A. Tonja
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE
Hassan Shakil
Hassan Shakil
Ph.D. Candidate in Computer Science, University of Colorado Colorado Springs (UCCS)
Large Language ModelsNatural Language Processing
S
Samer Iskandar
College of Engineering and Applied Science, University of Colorado Colorado Springs, Colorado Springs, 80918, CO, USA
Olga Kolesnikova
Olga Kolesnikova
Centro de Investigación en Computación (CIC) del Instituto Politécnico Nacional, Mexico
Artificial IntelligenceNatural Language ProcessingLinguistics
J
Jugal K. Kalita
College of Engineering and Applied Science, University of Colorado Colorado Springs, Colorado Springs, 80918, CO, USA