实体
Influence Functions
Influence Functions
PulseAugur coverage of Influence Functions — every cluster mentioning Influence Functions across labs, papers, and developer communities, ranked by signal.
总计 · 30天
3
90 天内 3
发布 · 30天
0
90 天内 0
论文 · 30天
3
90 天内 3
层级分布 · 90 天
情绪 · 30 天
1 天有情绪数据
最近 · 第 1/1 页 · 共 3 条
-
新的CLIF方法使用概念级影响函数增强NLP模型的可解释性
研究人员开发了CLIF，一种使用影响函数来提高NLP模型可解释性的新方法。该方法可以识别有益和有害的影响训练数据点，并通过调整这些样本来恢复性能，而无需重新训练。CLIF还分析了概念瓶颈模型内的概念级影响，从而深入了解决策过程。
-
New analysis reveals accuracy of AI data attribution methods
Researchers have developed a new mathematical analysis for data attribution methods like Influence Functions (IF) and Newton Step (NS) in convex learning problems. This analysis does not rely on strong convexity assumpt…
-
New dual representation for influence functions improves efficiency
Researchers have developed a new dual representation for influence functions, which can efficiently estimate changes in model parameters and outputs. This method scales with dataset size rather than model size, offering…