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.
☆344Oct 29, 2023Updated 2 years ago
Alternatives and similar repositories for pytorch_influence_functions
Users that are interested in pytorch_influence_functions are comparing it to the libraries listed below
Sorting:
- A simple PyTorch implementation of influence functions.☆92Jun 17, 2024Updated last year
- ☆51Mar 24, 2023Updated 2 years ago
- Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020☆64Apr 14, 2021Updated 4 years ago
- ☆64Apr 25, 2020Updated 5 years ago
- Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)☆239Feb 14, 2022Updated 4 years ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆184Jun 24, 2025Updated 8 months ago
- Tiny Tutorial on https://arxiv.org/abs/1703.04730☆14Nov 19, 2019Updated 6 years ago
- ☆63Jan 13, 2022Updated 4 years ago
- A simple Jax implementation of influence functions.☆20Apr 9, 2024Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆232Nov 18, 2024Updated last year
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆79Oct 3, 2024Updated last year
- ☆62Jun 8, 2021Updated 4 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97May 25, 2023Updated 2 years ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Dec 27, 2022Updated 3 years ago
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).☆52Jun 5, 2024Updated last year
- ☆32May 24, 2023Updated 2 years ago
- ☆10Oct 20, 2023Updated 2 years ago
- Code for the paper "Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction" …☆12Sep 6, 2023Updated 2 years ago
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆16Sep 15, 2023Updated 2 years ago
- ☆18Mar 1, 2022Updated 4 years ago
- Understanding Rare Spurious Correlations in Neural Network☆12Jun 5, 2022Updated 3 years ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Nov 27, 2023Updated 2 years ago
- Review and analysis of the ICML 2017 best paper: "Understanding Black-box Predictions via Influence Functions"☆12Mar 16, 2018Updated 7 years ago
- Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".☆13Sep 11, 2020Updated 5 years ago
- code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018☆67Sep 13, 2021Updated 4 years ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆143Feb 11, 2026Updated 2 weeks ago
- Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value (ICML 2023)☆21Jul 26, 2023Updated 2 years ago
- Official codes for "Understanding Deep Gradient Leakage via Inversion Influence Functions", NeurIPS 2023☆15Oct 13, 2023Updated 2 years ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆113Updated this week
- Detection of adversarial examples using influence functions and nearest neighbors☆37Nov 22, 2022Updated 3 years ago
- ☆26Jan 25, 2019Updated 7 years ago
- ☆14Feb 24, 2020Updated 6 years ago
- A Toolbox for Adversarial Robustness Research☆1,367Sep 14, 2023Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆140Jun 7, 2024Updated last year
- A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]☆90Mar 24, 2023Updated 2 years ago
- ☆112Jun 20, 2023Updated 2 years ago
- A simple and efficient baseline for data attribution☆11Nov 10, 2023Updated 2 years ago
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆25Dec 12, 2023Updated 2 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆73May 18, 2024Updated last year