Alternatives and similar repositories for interpretability-theory:

Users that are interested in interpretability-theory are comparing it to the libraries listed below

• facebookresearch / ModelRatatouille
  Recycling diverse models
  ☆44Updated 2 years ago
• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆20Updated last year
• MadryLab / modeldiff
  ModelDiff: A Framework for Comparing Learning Algorithms
  ☆56Updated last year
• ml-jku / quam
  Quantification of Uncertainty with Adversarial Models
  ☆28Updated last year
• JonasGeiping / dataaugs
  ☆17Updated 2 years ago
• shoaibahmed / metadata_archaeology
  Official code for the paper: "Metadata Archaeology"
  ☆19Updated last year
• alexrame / diwa
  DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization
  ☆30Updated 2 years ago
• socialfoundations / benchbench
  BenchBench is a Python package to evaluate multi-task benchmarks.
  ☆15Updated 9 months ago
• izmailovpavel / spurious_feature_learning
  ☆45Updated 2 years ago
• fgranese / DOCTOR
  Advances in Neural Information Processing Systems (NeurIPS 2021)
  ☆22Updated 2 years ago
• microsoft / augmented-interpretable-models
  Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
  ☆42Updated 2 months ago
• GT-RIPL / Geometric-Sensitivity-Decomposition
  ☆18Updated 3 years ago
• sjunhongshen / DASH
  ☆22Updated 2 years ago
• RandallBalestriero / SplineLLM
  ☆15Updated last year
• YeonwooSung / GLOM
  PyTorch implementation of GLOM
  ☆22Updated 3 years ago
• dmitrykazhdan / concept-based-xai
  Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
  ☆54Updated 2 years ago
• HazyResearch / mandoline
  (ICML 2021) Mandoline: Model Evaluation under Distribution Shift
  ☆31Updated 3 years ago
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆19Updated 3 months ago
• facebookresearch / grounding-inductive-biases
  reproduces experiments from "Grounding inductive biases in natural images: invariance stems from variations in data"
  ☆17Updated 7 months ago
• rtaori / data_feedback
  Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"
  ☆16Updated 2 years ago
• yannadani / cbed
  Official implementation of the paper "Interventions, Where and How? Experimental Design for Causal Models at Scale", NeurIPS 2022.
  ☆20Updated 2 years ago
• pomonam / jax-influence
  A simple Jax implementation of influence functions.
  ☆16Updated last year
• SuReLI / NeurOps
  Implementations of growing and pruning in neural networks
  ☆22Updated last year
• jiwoongim / OHO
  Online Hyperparameter Optimization
  ☆10Updated 4 years ago
• yiyixuxu / n-grammer-flax
  Implementation of N-Grammer in Flax
  ☆17Updated 2 years ago
• team-approx-bayes / bayesian-sam
  Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.
  ☆25Updated last year
• BatsResearch / nplm
  A weak supervision framework for (partial) labeling functions
  ☆16Updated 9 months ago
• ykwon0407 / beta_shapley
  Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)
  ☆40Updated 2 years ago
• benbo / interactive-weak-supervision
  Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling
  ☆31Updated 4 years ago
• SamsungSAILMontreal / PAPA
  Repository for the PopulAtion Parameter Averaging (PAPA) paper
  ☆26Updated last year