PyTorch Implementation of Influence Function

Jun 18, 2020 1 min read

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.

https://github.com/nimarb/pytorch_influence_functions
https://github.com/dedeswim/pytorch_influence_functions
https://github.com/nayopu/influence_function_with_lissa

Ryo Kamoi

Ryo Kamoi is a PhD student at Penn State University (2023-). His research interests lie in natural language processing (NLP) and large language models (LLMs), with a particular focus on building trustworthy NLP systems.