applicable models
gradient access
Requires access to model gradients
18 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Integrated Gradients | Algorithmic | Architecture/neural Networks Architecture/neural Networks/transformer +4 | Image Tabular Text | Integrated Gradients assigns input features scores for a prediction relative to a chosen reference input, called the... | ||
| Taylor Decomposition | Algorithmic | Requirements/model Internals Architecture/neural Networks +3 | Any | Taylor Decomposition explains one prediction of a neural network by splitting its output score into a contribution from... | ||
| Gradient Saliency | Algorithmic | Architecture/neural Networks Requirements/differentiable +2 | Image | Gradient saliency (also called vanilla gradient saliency) is the simplest gradient-based explanation for image... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +3 | Image | Grad-CAM (Gradient-weighted Class Activation Mapping) draws a heatmap over an image showing which regions most raise a... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +5 | Any | Influence functions estimate which training examples most affected a model's prediction on a particular test example.... | ||
| Contrastive Explanation Method | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | The Contrastive Explanation Method (CEM) explains one prediction of a classifier, such as a neural network, by... | ||
| Adversarial Debiasing | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Adversarial debiasing trains a model so that its predictions carry as little information as possible about a protected... | ||
| GAN-Based Tabular Synthetic Data | Algorithmic | Architecture/neural Networks/generative/gan Architecture/neural Networks/generative/vae +3 | Tabular | GAN-based tabular synthetic data generation trains a generative model on a real table, then samples new rows from it to... | ||
| Federated Learning | Algorithmic | Architecture/linear Models Architecture/neural Networks +4 | Any | Federated learning trains one shared model across several parties, such as phones or hospitals, without collecting their... | ||
| Concept Activation Vectors | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | A concept activation vector (CAV) is a direction inside a neural network that stands for a human idea such as 'stripes'.... | ||
| Fairness GAN | Algorithmic | Architecture/neural Networks/generative/gan Paradigm/generative +3 | Any | Fairness GAN is a pre-processing method that generates a synthetic training dataset in which decisions no longer track a... | ||
| Meta Fair Classifier | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | The meta fair classifier is a general-purpose training algorithm for fair classification. The user chooses a fairness... | ||
| Exponentiated Gradient Reduction | Algorithmic | Architecture/model Agnostic Paradigm/discriminative +4 | Any | Exponentiated gradient reduction trains a classifier that satisfies a chosen fairness criterion, such as demographic... | ||
| Learning Adversarially Fair and Transferable Representations | Algorithmic | Architecture/neural Networks Paradigm/parametric +4 | Image Tabular | Learning Adversarially Fair and Transferable Representations (LAFTR) trains an encoder that turns each record into a... | ||
| Data Poisoning Detection | Algorithmic | Architecture/model Agnostic Requirements/white Box +1 | Any | Data poisoning detection looks for training examples that an attacker has planted to change how a model behaves. The... | ||
| AutoAttack | Testing | Architecture/neural Networks Paradigm/supervised +2 | Image | AutoAttack is a fixed suite of four automated adversarial attacks, introduced by Croce and Hein (ICML 2020), that... | ||
| Differentially Private Stochastic Gradient Descent | Algorithmic | Architecture/neural Networks Paradigm/parametric +2 | Any | Differentially private stochastic gradient descent (DP-SGD) trains a neural network, or another model fitted by gradient... | ||
| GNNExplainer | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Graph | GNNExplainer explains one prediction of a graph neural network, a model that passes information along the edges of a... |
Rows per page
Page 1 of 1