A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911577049923584 |
|---|---|
| author | Islam, Md. Ariful Jahin, Md Abrar Mridha, M. F. Dey, Nilanjan |
| author_facet | Islam, Md. Ariful Jahin, Md Abrar Mridha, M. F. Dey, Nilanjan |
| contents | Explainable Artificial Intelligence (XAI) methods are increasingly used in safety-critical domains, yet there is no unified framework to jointly evaluate fidelity, interpretability, robustness, fairness, and completeness. We address this gap through two contributions. First, we propose a multi-criteria evaluation framework that formalizes these five criteria using principled metrics: fidelity via prediction-gap analysis; interpretability via a composite concentration-coherence-contrast score; robustness via cosine-similarity perturbation stability; fairness via Jensen-Shannon divergence across demographic groups; and completeness via feature-ablation coverage. These are integrated using an entropy-weighted dynamic scoring scheme that adapts to domain-specific priorities. Second, we introduce Perturbation-Gradient Consensus Attribution (PGCA), which fuses grid-based perturbation importance with Grad-CAM++ through consensus amplification and adaptive contrast enhancement, combining perturbation fidelity with gradient-based spatial precision. We evaluate across five domains (brain tumor MRI, plant disease, security screening, gender, and sunglass detection) using fine-tuned ResNet-50 models. PGCA achieves the best performance in fidelity $(2.22 \pm 1.62)$, interpretability $(3.89 \pm 0.33)$, and fairness $(4.95 \pm 0.03)$, with statistically significant improvements over baselines $(p < 10^{-7})$. Sensitivity analysis shows stable rankings (Kendall's $(τ\geq 0.88)$). Code and results are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03884 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution Islam, Md. Ariful Jahin, Md Abrar Mridha, M. F. Dey, Nilanjan Artificial Intelligence Explainable Artificial Intelligence (XAI) methods are increasingly used in safety-critical domains, yet there is no unified framework to jointly evaluate fidelity, interpretability, robustness, fairness, and completeness. We address this gap through two contributions. First, we propose a multi-criteria evaluation framework that formalizes these five criteria using principled metrics: fidelity via prediction-gap analysis; interpretability via a composite concentration-coherence-contrast score; robustness via cosine-similarity perturbation stability; fairness via Jensen-Shannon divergence across demographic groups; and completeness via feature-ablation coverage. These are integrated using an entropy-weighted dynamic scoring scheme that adapts to domain-specific priorities. Second, we introduce Perturbation-Gradient Consensus Attribution (PGCA), which fuses grid-based perturbation importance with Grad-CAM++ through consensus amplification and adaptive contrast enhancement, combining perturbation fidelity with gradient-based spatial precision. We evaluate across five domains (brain tumor MRI, plant disease, security screening, gender, and sunglass detection) using fine-tuned ResNet-50 models. PGCA achieves the best performance in fidelity $(2.22 \pm 1.62)$, interpretability $(3.89 \pm 0.33)$, and fairness $(4.95 \pm 0.03)$, with statistically significant improvements over baselines $(p < 10^{-7})$. Sensitivity analysis shows stable rankings (Kendall's $(τ\geq 0.88)$). Code and results are publicly available. |
| title | A Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.03884 |