Popular GitHub Repositories for Authorship Attribution

LightweightMMM ? is a lightweight Bayesian Marketing Mix Modeling (MMM) library that allows users to easily train MMMs and obtain channel attribution information.

Diffusion attentive attribution maps for interpreting Stable Diffusion.

Interpretability for sequence generation models ? ?

Pytorch Implementation of recent visual attribution methods for model interpretability

Collection of NLP model explanations and accompanying analysis tools

A curated list of awesome machine learning libraries for marketing, including media mix models, multi touch attribution, causal inference and more

Implementation of Visual Feature Attribution using Wasserstein GANs (VAGANs, https://arxiv.org/abs/1711.08998) in PyTorch

Evaluating Data Attribution for Text-to-Image Models: a visual data attribution benchmark for evaluating and learning training image influences.

Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"

LLM Attributor: Attribute LLM's Generated Text to Training Data

A set of notebooks as a guide to the process of fine-grained image classification of birds species, using PyTorch based deep neural networks.

Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)

On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification

Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"

surrogate quantitative interpretability for deepnets

Source code of NeurIPS 2022 accepted paper "AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning"

ComfyUI custom nodes for Diffusion Attentive Attribution Maps (DAAM)

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models (CVPR 2024)

[IEEE Transactions on Power Systems] Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution Map

Counterfactual SHAP: a framework for counterfactual feature importance