博士生讨论班2025[25]
时间：2025-11-25
阅读量：147次
- 演讲人： 申百宁
- 时间：2025年11月25日14:00
- 地点：浙江大学紫金港校区行政楼1417报告厅
- 主办单位：浙江大学数据科学研究中心
报告文章：Improving performance of deep learning models with axiomatic attribution priors and expected gradients
摘要：Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties—most frequently, that particular features are important or unimportant. These attribution priors are often based on attribution methods that are not guaranteed to satisfy desirable interpretability axioms, such as completeness and implementation invariance. Here we introduce attribution priors to optimize for higher-level properties of explanations, such as smoothness and sparsity, enabled by a fast new attribution method formulation called expected gradients that satisfies many important interpretability axioms. This improves model performance on many real-world tasks where previous attribution priors fail.