Official implementation for the paper " How Many and Which Training Points Would Need to be Removed to Flip this Prediction?"
- The Algorithm 1 is in
IP
function underSmallest_k.py
. The Algorithm 2 is inrecursive_NT
function underiterative.py
. - To run algorithms for the
SST
dataset, you can use the command below:
mkdir results
python SST.py
- To run algorithms for the
SST
feature extracted from BERT, you can use the command:
python SST_bert.py
- You can download other processed datasets and hyperparameter information via https://huggingface.co/datasets/Eciel/Smallest_k_experiment.