GitHub topics: influence-functions
nimarb/pytorch_influence_functions
This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
Language: Python - Size: 448 KB - Last synced at: 7 days ago - Pushed at: over 1 year ago - Stars: 332 - Forks: 71

deel-ai/influenciae
đź‘‹ Influenciae is a Tensorflow Toolbox for Influence Functions
Language: Python - Size: 2.03 MB - Last synced at: 5 days ago - Pushed at: about 1 year ago - Stars: 63 - Forks: 5

aai-institute/pyDVL
pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation
Language: Python - Size: 435 MB - Last synced at: 12 days ago - Pushed at: 12 days ago - Stars: 124 - Forks: 7

pomonam/kronfluence
Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature
Language: Python - Size: 22 MB - Last synced at: 27 days ago - Pushed at: 10 months ago - Stars: 145 - Forks: 15

alstonlo/torch-influence
A simple PyTorch implementation of influence functions.
Language: Python - Size: 6.94 MB - Last synced at: about 1 month ago - Pushed at: 11 months ago - Stars: 86 - Forks: 11

Linxyhaha/DEALRec
Data-efficient Fine-tuning for LLM-based Recommendation (SIGIR'24)
Language: Python - Size: 52.8 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 25 - Forks: 3

mintaywon/IF_RLHF
Source code for 'Understanding impacts of human feedback via influence functions'
Language: Python - Size: 106 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 4 - Forks: 0

yzhang511/TimeInf
Time series data contribution via influence functions
Language: Python - Size: 146 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 8 - Forks: 0

hslyu/GIF
Official implementation of "Deeper Understanding of Black-box Predictions via Generalized Influence Functions".
Language: Jupyter Notebook - Size: 5 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 8 - Forks: 0

pomonam/jax-influence
A simple Jax implementation of influence functions.
Language: Python - Size: 39.1 KB - Last synced at: about 1 month ago - Pushed at: about 1 year ago - Stars: 16 - Forks: 0

bsharchilev/influence_boosting
Supporting code for the paper "Finding Influential Training Samples for Gradient Boosted Decision Trees"
Language: Python - Size: 16.1 MB - Last synced at: about 2 months ago - Pushed at: 12 months ago - Stars: 67 - Forks: 18

xszheng2020/Classical-LOO
Leave One Out
Language: Jupyter Notebook - Size: 2.62 MB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 1 - Forks: 0

jjbrophy47/tree_influence
Influence Estimation for Gradient-Boosted Decision Trees
Language: Python - Size: 5.38 MB - Last synced at: 9 months ago - Pushed at: 12 months ago - Stars: 23 - Forks: 9

RyanWangZf/Influence_Subsampling
Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020
Language: Python - Size: 11 MB - Last synced at: 12 months ago - Pushed at: about 4 years ago - Stars: 65 - Forks: 15

sail-sg/D-TRAK
Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
Language: Jupyter Notebook - Size: 39.3 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 15 - Forks: 1

ShinKyuY/Understanding_Black_box_Predictions_via_Influence_Functions_tutorial_MNIST
Tiny Tutorial on https://arxiv.org/abs/1703.04730
Language: Jupyter Notebook - Size: 5.6 MB - Last synced at: over 1 year ago - Pushed at: over 5 years ago - Stars: 12 - Forks: 2

ryokamoi/pytorch_influence_functions Fork of nimarb/pytorch_influence_functions
This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
Language: Python - Size: 470 KB - Last synced at: almost 2 years ago - Pushed at: almost 5 years ago - Stars: 14 - Forks: 4

feifeiobama/InfluenceCL
[CVPR 2023] Regularizing Second-Order Influences for Continual Learning
Language: Python - Size: 420 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 18 - Forks: 0

HKUNLP/ProGen
[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.
Language: Python - Size: 970 KB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 11 - Forks: 0

MortonWang/geo_IF
This is an implementation of the paper ”Interpreting Twitter User Geolocation“.
Language: Python - Size: 8.48 MB - Last synced at: about 1 month ago - Pushed at: almost 2 years ago - Stars: 5 - Forks: 0

ICDM-Lab/geo_IF
This repo provides an implementation of the paper Interpreting Twitter User Geolocation.
Language: Python - Size: 8.48 MB - Last synced at: about 2 years ago - Pushed at: almost 3 years ago - Stars: 3 - Forks: 0

sungyubkim/if_classic
A brief notebook on Influence Function (IF) for classical generative models (e.g., k-NN, KDE, GMM)
Language: Jupyter Notebook - Size: 2.83 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 0

ajsanjoaquin/pytorch_influence_functions Fork of nimarb/pytorch_influence_functions
This is a [Stable] PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
Language: Python - Size: 547 KB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 1 - Forks: 1
