applicable models
gradient access
Requires access to model gradients
18 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Integrated Gradients | Algorithmic | Architecture/neural Networks Paradigm/parametric +3 | Any | Integrated Gradients is an attribution technique that explains a model's prediction by quantifying the contribution of... | ||
| Taylor Decomposition | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | Taylor Decomposition is a mathematical technique that explains neural network predictions by computing first-order and... | ||
| Saliency Maps | Algorithmic | Architecture/neural Networks Requirements/differentiable +1 | Image | Saliency maps are visual explanations for image classification models that highlight which pixels in an image most... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +2 | Image | Grad-CAM creates visual heatmaps showing which regions of an image a convolutional neural network focuses on when making... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +6 | Any | Influence functions quantify how much each training example influenced a model's predictions by computing the change in... | ||
| Contrastive Explanation Method | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | The Contrastive Explanation Method (CEM) explains model decisions by generating contrastive examples that reveal what... | ||
| Adversarial Debiasing | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Adversarial debiasing reduces bias by training models using a competitive adversarial setup, similar to Generative... | ||
| Federated Learning | Algorithmic | Architecture/linear Models Architecture/neural Networks +4 | Any | Federated learning enables collaborative model training across multiple distributed parties (devices, organisations, or... | ||
| Model Pruning | Algorithmic | Architecture/neural Networks Paradigm/parametric +4 | Any | Model pruning systematically removes less important weights, neurons, or entire layers from neural networks to create... | ||
| Feature Attribution with Integrated Gradients in NLP | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +4 | Text | Applies Integrated Gradients to natural language processing models to attribute prediction importance to individual... | ||
| Concept Activation Vectors | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | Concept Activation Vectors (CAVs), also known as Testing with Concept Activation Vectors (TCAV), identify mathematical... | ||
| Fairness GAN | Algorithmic | Architecture/neural Networks/generative/gan Paradigm/generative +4 | Any | A data generation technique that employs Generative Adversarial Networks (GANs) to create fair synthetic datasets by... | ||
| Fair Adversarial Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +6 | Any | An in-processing fairness technique that employs adversarial training with dual neural networks to learn fair... | ||
| Meta Fair Classifier | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | An in-processing fairness technique that employs meta-learning to modify any existing classifier for optimising fairness... | ||
| Exponentiated Gradient Reduction | Algorithmic | Architecture/model Agnostic Paradigm/discriminative +5 | Any | An in-processing fairness technique based on Agarwal et al.'s reductions approach that transforms fair classification... | ||
| Fair Transfer Learning | Algorithmic | Architecture/neural Networks Paradigm/parametric +4 | Any | An in-processing fairness technique that adapts pre-trained models from one domain to another whilst explicitly... | ||
| Bayesian Fairness Regularization | Algorithmic | Architecture/model Agnostic Paradigm/parametric +4 | Any | Bayesian Fairness Regularization incorporates fairness constraints into machine learning models through Bayesian... | ||
| Data Poisoning Detection | Algorithmic | Architecture/model Agnostic Requirements/white Box +1 | Any | Data poisoning detection identifies malicious training data designed to compromise model behaviour. This technique... |
Rows per page
Page 1 of 1