dilyabareeva / quanda
A toolkit for quantitative evaluation of data attribution methods.
☆32Updated this week
Related projects ⓘ
Alternatives and complementary repositories for quanda
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆30Updated 6 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆118Updated 5 months ago
- ☆27Updated 3 months ago
- Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curv…☆13Updated 2 years ago
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept dat…☆79Updated 7 months ago
- Existing literature about training-data analysis.☆17Updated 2 years ago
- A Data-Centric library providing a unified interface for state-of-the-art methods for hardness characterisation of data points.☆23Updated last month
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paper…☆52Updated this week
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆99Updated last year
- Official Code Implementation of the paper : XAI for Transformers: Better Explanations through Conservative Propagation☆61Updated 2 years ago
- Official repository of ICML 2023 paper: Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat☆23Updated 7 months ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆104Updated last month
- Pytorch library for model calibration metrics and visualizations as well as recalibration methods. In progress!☆68Updated 6 months ago
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Updated 9 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆72Updated 5 months ago
- ☆17Updated 2 months ago
- The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era comp…☆83Updated last year
- bayesian lime☆16Updated 3 months ago
- OpenDataVal: a Unified Benchmark for Data Valuation in Python (NeurIPS 2023)☆86Updated 3 months ago
- CoSy: Evaluating Textual Explanations☆14Updated last month
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based models☆25Updated last year
- A repository for summaries of recent explainable AI/Interpretable ML approaches☆65Updated last month
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆200Updated 3 months ago
- A benchmark for distribution shift in tabular data☆43Updated 5 months ago
- Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆97Updated this week
- Generate robust counterfactual explanations for machine learning models☆14Updated last year
- An Empirical Framework for Domain Generalization In Clinical Settings☆27Updated 2 years ago
- Neural Additive Models (Google Research)☆26Updated 6 months ago
- A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.☆78Updated 2 years ago
- Official repository for the ICLR 2023 paper "A Learning Based Hypothesis Test for Harmful Covariate Shift"☆12Updated 9 months ago