Prototype and Criticism Models

Description

Prototype and Criticism Models provide data understanding by identifying two complementary sets of examples: prototypes represent the most typical instances that best summarise common patterns in the data, whilst criticisms are outliers or edge cases that are poorly represented by the prototypes. For example, in a dataset of customer transactions, prototypes might be the most representative buying patterns (frequent small purchases, occasional large purchases), whilst criticisms could be unusual behaviors (bulk buyers, one-time high-value customers). This dual approach reveals both what is normal and what is exceptional, helping understand data coverage and model blind spots.

Example Use Cases

Explainability

Analysing medical imaging datasets to identify prototype scans that represent typical healthy tissue patterns and criticism examples showing rare disease presentations, helping radiologists understand what the model considers 'normal' versus cases requiring special attention.

Evaluating credit scoring models by finding prototype borrowers who represent typical low-risk profiles and criticism cases showing unusual but legitimate financial patterns that the model might misclassify, ensuring fair treatment of edge cases.

Fairness

Evaluating representation bias in hiring datasets by examining whether prototypes systematically exclude certain demographic groups and criticisms disproportionately represent minorities, revealing data collection inequities.

Limitations

Selection of prototypes and criticisms is highly dependent on the choice of distance metric or similarity measure, which may not capture all meaningful relationships in the data.
Computational complexity can become prohibitive for very large datasets, as the method often requires pairwise comparisons or optimisation over the entire dataset.
The number of prototypes and criticisms to select is typically a hyperparameter that requires domain expertise to set appropriately.
Results may not generalise well if the training data distribution differs significantly from the deployment data distribution.

Resources

Examples are not Enough, Learn to Criticize! Criticism for Interpretability

Research Paper•Been Kim, Rajiv Khanna, and Oluwasanmi O. Koyejo•Dec 5, 2016

SeldonIO/alibi

Software Package

Prototype Selection for Interpretable Classification

Research Paper•Oscar Reyes, Carlos Morell, and Sebastian Ventura•Feb 27, 2012

Alibi Explain Documentation

Documentation

Related Techniques

Name	Description	Assurance Goals
Area Under Precision-Recall Curve	Area Under Precision-Recall Curve (AUPRC) measures model performance by plotting precision (the proportion of positive predictions that are correct) against recall (the proportion of actual positives that are correctly identified) at various classification thresholds, then calculating the area under the resulting curve. Unlike accuracy or AUC-ROC, AUPRC is particularly valuable for imbalanced datasets where the minority class is of primary interest---a perfect score is 1.0, whilst random performance equals the positive class proportion. By focusing on the precision-recall trade-off, it provides a more informative assessment than overall accuracy for scenarios where false positives and false negatives have different costs, especially when positive examples are rare.	Reliability Transparency Fairness
Counterfactual Fairness Assessment	Counterfactual Fairness Assessment evaluates whether a model's predictions would remain unchanged if an individual's protected attributes (race, gender, age) were different, whilst keeping all other causally legitimate factors constant. The technique requires constructing a causal graph that maps relationships between variables, then using do-calculus or structural causal models to simulate counterfactual scenarios. For example, it asks: 'Would this loan application still be approved if the applicant were a different race, holding constant their actual qualifications and economic circumstances?' This individual-level fairness criterion helps identify when decisions depend improperly on protected characteristics.	Fairness
Temperature Scaling	Temperature scaling adjusts a model's confidence by applying a single parameter (temperature) to its predictions. When a model is too confident in its wrong answers, temperature scaling can fix this by making the predictions more realistic. It works by dividing the model's outputs by the temperature value before converting them to probabilities. Higher temperatures make the model less confident, whilst lower temperatures increase confidence. The technique maintains the model's accuracy whilst ensuring that when it says it's 90% confident, it's actually right about 90% of the time.	Reliability Transparency Fairness
Saliency Maps	Saliency maps are visual explanations for image classification models that highlight which pixels in an image most strongly influence the model's prediction. Computed by calculating gradients of the model's output with respect to input pixels, saliency maps produce heatmaps where brighter regions indicate pixels that, when changed, would most significantly affect the prediction. This technique helps users understand which parts of an image the model is 'looking at' when making decisions.	Explainability Fairness
Conformal Prediction	Conformal prediction provides mathematically guaranteed uncertainty quantification by creating prediction sets that contain the true outcome with a specified probability (e.g., exactly 95% coverage). The technique works by measuring how 'strange' or 'nonconforming' new predictions are compared to calibration data - if a prediction seems unusual, it gets wider intervals. For example, in medical diagnosis, instead of saying 'likely cancer', it might say 'possible diagnoses: {cancer, benign tumour} with 95% confidence'. This distribution-free method works with any underlying model (neural networks, random forests, etc.) and requires no assumptions about data distribution, making it a robust framework for reliable uncertainty estimates in high-stakes applications.	Reliability Transparency Fairness
Factor Analysis	Factor analysis is a statistical technique that identifies latent variables (hidden factors) underlying observed correlations in data. It works by analysing how variables relate to each other, finding a smaller number of unobserved factors that explain patterns among multiple observed variables. Unlike PCA which maximises total variance, factor analysis focuses on shared variance (communalities - the variance variables have in common) whilst separating out unique variance and measurement error. After extracting factors, rotation methods like varimax (which creates uncorrelated factors) or oblimin (allowing correlated factors) help make factors more interpretable by aligning them with distinct groups of variables.	Explainability Transparency