A fast, effective data attribution method for neural networks in PyTorch
☆243Nov 18, 2024Updated last year
Alternatives and similar repositories for trak
Users that are interested in trak are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Data for "Datamodels: Predicting Predictions with Training Data"☆97May 25, 2023Updated 3 years ago
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆90Feb 27, 2024Updated 2 years ago
- ☆32May 24, 2023Updated 3 years ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆198May 23, 2026Updated last month
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆124Mar 24, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆53Jan 24, 2024Updated 2 years ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆40Dec 27, 2022Updated 3 years ago
- Code for the paper "The Journey, Not the Destination: How Data Guides Diffusion Models"☆25Dec 12, 2023Updated 2 years ago
- ☆33Feb 11, 2025Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆60Aug 15, 2023Updated 2 years ago
- Code for NeurIPS'23 paper "A Bayesian Approach To Analysing Training Data Attribution In Deep Learning"☆17Jan 12, 2024Updated 2 years ago
- Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)☆242Feb 14, 2022Updated 4 years ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆39Jan 23, 2024Updated 2 years ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆531Oct 20, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence…☆348Oct 29, 2023Updated 2 years ago
- A toolkit for quantitative evaluation of data attribution methods.☆60May 11, 2026Updated 2 months ago
- ☆44Oct 13, 2023Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆147Jun 7, 2024Updated 2 years ago
- Debiasing Through Data Attribution☆13May 23, 2024Updated 2 years ago
- Official repository for MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models [NeurIPS 2024]☆80Nov 14, 2024Updated last year
- Attribute (or cite) statements generated by LLMs back to in-context information.☆337Oct 8, 2024Updated last year
- A simple PyTorch implementation of influence functions.☆96Jun 17, 2024Updated 2 years ago
- A simple and efficient baseline for data attribution☆11Nov 10, 2023Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Distilling Model Failures as Directions in Latent Space☆48Feb 8, 2023Updated 3 years ago
- ☆66Jan 13, 2022Updated 4 years ago
- OpenDataVal: a Unified Benchmark for Data Valuation in Python (NeurIPS 2023)☆101Feb 4, 2025Updated last year
- Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific a…☆19Dec 25, 2024Updated last year
- Code for paper: “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability through Influence-Based Data Selecti…☆23May 17, 2024Updated 2 years ago
- ☆15Jul 24, 2022Updated 3 years ago
- ☆217Oct 10, 2022Updated 3 years ago
- Code for coreset selection methods☆257Feb 27, 2023Updated 3 years ago
- Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"☆31Jul 8, 2020Updated 6 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆45Feb 27, 2023Updated 3 years ago
- Decomposing and Editing Predictions by Modeling Model Computation☆138Jun 12, 2024Updated 2 years ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated 2 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆125Feb 11, 2025Updated last year
- DSIR large-scale data selection framework for language model training☆275Apr 7, 2024Updated 2 years ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆357Dec 26, 2023Updated 2 years ago