applicable models
white box
Requires full model transparency and access
39 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Mean Decrease Impurity | Algorithmic | Architecture/tree Based Paradigm/supervised +1 | Tabular | Mean Decrease Impurity (MDI) scores how much each feature contributes to a tree-based model, such as a random forest, by... | ||
| Coefficient Magnitudes (in Linear Models) | Metric | Architecture/linear Models Paradigm/parametric +2 | Tabular | Coefficient Magnitudes explains a linear model by reading its fitted coefficients. Each coefficient shows how much the... | ||
| DeepLIFT | Algorithmic | Requirements/model Internals Architecture/neural Networks +2 | Any | DeepLIFT (Deep Learning Important FeaTures) explains a single prediction of a neural network by dividing the difference... | ||
| Layer-wise Relevance Propagation | Algorithmic | Requirements/model Internals Architecture/neural Networks +3 | Any | Layer-wise Relevance Propagation (LRP) explains a neural network's prediction by working backwards from the output to... | ||
| Contextual Decomposition | Algorithmic | Architecture/neural Networks/recurrent Requirements/white Box +1 | Text | Contextual Decomposition explains why an LSTM, a neural network that reads text one word at a time, made a particular... | ||
| 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-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... | ||
| Out-of-Distribution Detector for Neural Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +3 | Image | ODIN (Out-of-Distribution Detector for Neural Networks) flags inputs that look unlike the data a neural network... | ||
| 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... | ||
| 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... | ||
| Homomorphic Encryption | Algorithmic | Architecture/linear Models Architecture/model Agnostic +5 | Any | Homomorphic encryption lets a server compute on data that stays encrypted, so the server never sees the underlying... | ||
| Quantile Regression | Algorithmic | Architecture/linear Models/regression Architecture/neural Networks +4 | Tabular | Quantile regression predicts chosen percentiles of an outcome, such as the 10th, 50th and 90th, rather than only its... | ||
| Temperature Scaling | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Temperature scaling is a correction applied after training to a classifier that is more confident than it is accurate, a... | ||
| Deep Ensembles | Algorithmic | Architecture/neural Networks Paradigm/parametric +2 | Any | Deep ensembles estimate how uncertain a neural network's predictions are by training several copies of the same network... | ||
| Monotonicity Constraints | Algorithmic | Architecture/neural Networks Architecture/probabilistic/gaussian Processes +3 | Tabular | Monotonicity constraints require a model's prediction to move only one way as a chosen input rises, with the other... | ||
| Generalized Additive Models | Algorithmic | Architecture/linear Models/gam Paradigm/parametric +2 | Tabular | A generalised additive model (GAM) builds its prediction by adding a baseline and one smooth curve for each input... | ||
| Neuron Activation Analysis | Algorithmic | Architecture/neural Networks Requirements/model Internals +1 | Text | Neuron activation analysis examines when individual neurons in a neural network respond strongly. The analyst runs a set... | ||
| Causal Mediation Analysis in Language Models | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +3 | Text | Causal mediation analysis traces which internal components of a language model carry the effect of a change in the input... |
Rows per page
Page 1 of 2