PyTorch Implementation of Influence Function
Influence function for neural networks is proposed in the ICML2017 best paper (Wei Koh & Liang, 2017). However, to the best of my knowledge, there is no generic PyTorch implementation with reliable test codes. Based on some existing implementations, I’m developing reliable Pytorch implementation of influence function.
- https://github.com/ryokamoi/pytorch_influence_functions
- https://github.com/ryokamoi/test_pytorch_influence_functions
My repositories are forks of the following great work.
Ryo Kamoi
Ryo Kamoi is a PhD candidate at Penn State University, supported by 2026 Google PhD Fellowship. His research focuses on self-evolving LLM agents and LLM-based verification of LLM responses and intermediate steps.