New Weighted Integrated Gradients method enhances AI feature attribution reliability

Researchers have introduced Weighted Integrated Gradients (WG), a novel method to improve the reliability of feature attribution in explainable AI, particularly for computer vision models. Unlike existing methods like Expected Gradients (EG) that treat all baseline images equally, WG adaptively selects and weights baselines based on their informativeness for a given input. This approach, which maintains the axiomatic properties of Integrated Gradients, showed up to a 36% improvement in attribution reliability over EG across various convolutional and Transformer architectures on common image datasets. The trade-off for this enhanced fidelity is a slight increase in computational cost due to the baseline suitability evaluation. AI

IMPACT Enhances reliability of AI model explanations, improving understanding and usability of computer vision models.

RANK_REASON The cluster contains an academic paper detailing a new method for explainable AI. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• Anh Nguyen
• arXiv
• CatalyzeX
• Connected Papers
• DagsHub
• Expected Gradients
• Gotit.pub
• Hugging Face
• Integrated Gradients
• Litmaps
• ScienceCast
• scite Smart Citations
• Weighted Integrated Gradients

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →