google-research / interpretability-theory

Related projects ⓘ

Alternatives and complementary repositories for interpretability-theory

• JonasGeiping / dataaugs
  ☆17Updated 2 years ago
• facebookresearch / ModelRatatouille
  Recycling diverse models
  ☆44Updated last year
• MadryLab / modeldiff
  ModelDiff: A Framework for Comparing Learning Algorithms
  ☆53Updated last year
• shoaibahmed / metadata_archaeology
  Official code for the paper: "Metadata Archaeology"
  ☆18Updated last year
• sjunhongshen / DASH
  ☆21Updated last year
• izmailovpavel / spurious_feature_learning
  ☆41Updated last year
• ml-jku / quam
  Quantification of Uncertainty with Adversarial Models
  ☆27Updated last year
• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆19Updated last year
• RandallBalestriero / SplineLLM
  ☆14Updated 11 months ago
• alexrame / diwa
  DiWA: Diverse Weight Averaging for Out-of-Distribution Generalization
  ☆28Updated last year
• xu-ji / information-bottleneck
  Deep Learning & Information Bottleneck
  ☆50Updated last year
• ae-foster / invclr
  Improving Transformation Invariance in Contrastive Representation Learning
  ☆13Updated 3 years ago
• GT-RIPL / Geometric-Sensitivity-Decomposition
  ☆18Updated 3 years ago
• joshr17 / IFM
  Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.
  ☆47Updated 2 years ago
• google-deepmind / ssl_hsic
  ☆35Updated 3 months ago
• SamsungSAILMontreal / PAPA
  Repository for the PopulAtion Parameter Averaging (PAPA) paper
  ☆26Updated 7 months ago
• team-approx-bayes / bayesian-sam
  Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.
  ☆23Updated last year
• ema-marconato / glancenet
  Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based models
  ☆25Updated last year
• aniruddhraghu / meta-pretraining
  Code accompanying paper: Meta-Learning to Improve Pre-Training
  ☆37Updated 3 years ago
• ykwon0407 / beta_shapley
  Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)
  ☆40Updated 2 years ago
• rtaori / data_feedback
  Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"
  ☆15Updated 2 years ago
• MadryLab / datamodels
  ☆22Updated last year
• mfederici / dsit
  Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"
  ☆25Updated 3 years ago
• HazyResearch / model-patching
  Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
  ☆42Updated 4 years ago
• ganguli-lab / degrees-of-freedom
  ☆36Updated 2 years ago
• facebookresearch / DejaVu
  Repository for the paper Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
  ☆37Updated last year
• EleutherAI / mdl
  Minimum Description Length probing for neural network representations
  ☆16Updated last week
• BatsResearch / nplm
  A weak supervision framework for (partial) labeling functions
  ☆14Updated 4 months ago
• fgranese / DOCTOR
  Advances in Neural Information Processing Systems (NeurIPS 2021)
  ☆22Updated 2 years ago
• facebookresearch / BalancingGroups
  Simple data balancing baselines for worst-group-accuracy benchmarks.
  ☆40Updated last year