Gradient Interpretability

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Dec 1 2:23
Editor
Edited
Edited
2025 Aug 8 0:23
Gradient is the connection line that enables causal interaction between different components, and
Residual Connection
enables this global causal connection without spatial restriction.
Gradient Interpretability Methods
 
 
 
Tracking dataset influence by remove noisy datapoints
Estimating Training Data Influence by Tracing Gradient Descent
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the...
Estimating Training Data Influence by Tracing Gradient Descent
Filter for the data to finetune based on gradient
arxiv.org
 
 

Recommendations