Gradient Interpretability

Creator

Creator

Seonglae Cho

Created

Created

2024 Dec 1 2:23

Editor

Editor

Seonglae Cho

Edited

Edited

2025 Aug 8 0:23

Refs

Refs

Back Propagation

Weight Interpretability

Model Interpretability

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

Integrated Gap Gradients

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...

https://arxiv.org/abs/2002.08484

Filter for the data to finetune based on gradient

https://arxiv.org/pdf/2402.04333

Recommendations

/////////