![_images/logo.png](_images/logo.png)
dattri: A Library for Efficient Data Attribution¶
dattri is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms. You may use dattri to
Deploy existing data attribution methods to PyTorch models - e.g., Influence Function, TracIn, RPS, TRAK, …
Develop new data attribution methods with efficient implementation of low-level utility functions - e.g., HVP/IHVP, random projection, dropout ensembling, …
Benchmark data attribution methods with standard benchmark settings - e.g., MNIST-10+LR/MLP, CIFAR-10/2+ResNet-9, MAESTRO + Music Transformer, Shakespeare + nanoGPT, …
Attribution Methods:
Low-level Utility Functions:
Benchmark: