dilyabareeva / quandaLinks
A toolkit for quantitative evaluation of data attribution methods.
β53Updated 2 months ago
Alternatives and similar repositories for quanda
Users that are interested in quanda are comparing it to the libraries listed below
Sorting:
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ39Updated last year
- π Overcomplete is a Vision-based SAE Toolboxβ79Updated last month
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]β189Updated 2 months ago
- Inference code for "TabDPT: Scaling Tabular Foundation Models on Real Data"β56Updated last week
- A fast, effective data attribution method for neural networks in PyTorchβ217Updated 10 months ago
- Research on Tabular Foundation Modelsβ56Updated 9 months ago
- Training and evaluating NBM and SPAM for interpretable machine learning.β78Updated 2 years ago
- OpenXAI : Towards a Transparent Evaluation of Model Explanationsβ247Updated last year
- Mechanistic understanding and validation of large AI models with SemanticLensβ31Updated this week
- XAI-Bench is a library for benchmarking feature attribution explainability techniquesβ70Updated 2 years ago
- Conformal prediction for controlling monotonic risk functions. Simple accompanying PyTorch code for conformal risk control in computer viβ¦β68Updated 2 years ago
- A simple PyTorch implementation of influence functions.β91Updated last year
- Conformal Language Modelingβ32Updated last year
- Influence Analysis and Estimation - Survey, Papers, and Taxonomyβ82Updated last year
- β30Updated 2 years ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β19Updated last year
- β121Updated this week
- relplot: Utilities for measuring calibration and plotting reliability diagramsβ168Updated 2 months ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β66Updated 2 years ago
- Framework code with wandb, checkpointing, logging, configs, experimental protocols. Useful for fine-tuning models or training from scratcβ¦β152Updated 2 years ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computationβ136Updated 2 weeks ago
- NumPy library for calibration metricsβ73Updated 6 months ago
- β47Updated 10 months ago
- β61Updated 3 years ago
- Attribution-based Parameter Decompositionβ30Updated 3 months ago
- PyTorch Explain: Interpretable Deep Learning in Python.β161Updated last year
- Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AIβ54Updated 3 years ago
- Influence Estimation for Gradient-Boosted Decision Treesβ30Updated last year
- β26Updated 7 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ130Updated last year