New method clusters disease subtypes from model explanations.
problem Discovering disease subtypes in noisy, high-dimensional data.
method Train classifier, extract explanations, cluster in explanation space.
result Cluster analysis on model explanations outperforms classical methods.
Proposes a deterministic LIME for CAD systems.
problem Instability in LIME explanations.
method Uses agglomerative HC and KNN to select relevant clusters and trains a linear model.
result DLIME is more stable than LIME.
Paper uses Shapley values to explain how clusters of training data affect predictions.
problem Explaining how training data clusters impact predictions from black-box models.
method Extends Shapley values to cluster importance, using coalitional game theory.
result Shows how different clusters of training data contribute to model predictions.
CLASSIX is a fast and explainable clustering method that sorts data and merges groups.
problem Clustering of data with various shapes and dimensions.
method Greedy aggregation followed by cluster merging with scalar parameters.
result CLASSIX performs competitively with state-of-the-art algorithms and provides intuitive explanations.
RELAX provides first attribution-based explanations for representations.
problem Lack of methods to explain what influences learned representations.
method RELAX, a first approach for attribution-based explanations of representations, measuring similarities in representation space.
result Significantly outperforms gradient-based baseline and models uncertainty in explanations.
New method explains cluster assignments in neural networks.
problem Lack of explainability in cluster models.
method Rewriting clustering models as neural networks.
result Ability to attribute cluster predictions to input features.
Improved interpretability methods for ML models using local regressions and variable importance.
problem Inability of existing interpretability methods to provide reliable explanations for ML models, especially in high-dimensional problems with irrelevant features and non-linear relationships.
method Introduces VarImp and SupClus methods using local regressions with weighted distance considering variable importance.
result VarImp and SupClus methods yield better explanations than state-of-the-art approaches, especially in high-dimensional problems with irrelevant features and non-linear relationships.
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning st…
In this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, rather than giving post-hoc explanations of a black-box model. The second is implementing discrete k-means with a differentiable neural net…
Stock markets can be characterized by fat tails in the volatility distribution, clustering of volatilities and slow decay of their time correlations. For an explanation models with several mechanisms and consequently many parameters as the Lux-Marchesi model have been used. We show that a simple herding model with only…
Proposes a method for multilevel explanations of black-box models.
problem Need for explanations at intermediate or group levels, especially for GDPR compliance.
method Meta-method that builds a multilevel explanation tree using local explainability methods.
result Effective multilevel explanations for groups of data points, including novel test points.
New clustering method adapts to data structure.
problem Natural adaptability of clustering order in EM algorithm.
method Minimizes mixing entropy to define relative entropic order.
result Empirical relative entropic order is consistent.
This paper optimizes clustering interpretability by balancing value and user-defined features.
problem Generating interpretable clusters in graph data.
method Proposes a β-interpretable clustering algorithm that ensures at least β fraction of nodes share the same feature value.
result Empirical demonstration of the benefits of the proposed approaches in generating interpretable clusters.
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
Proposes a constraint for deep clustering to handle both simple and complex topologies.
problem Limited prior knowledge for deep clustering methods to perform well on complex topologies.
method Introduces a constraint using symmetric InfoNCE to enhance deep clustering performance.
result The constraint improves deep clustering methods' performance on both simple and complex topologies.
Cluster LOCO: A model-agnostic feature importance score for interpreting cluster outputs
problem Interpreting and auditing cluster outputs
method Cluster LOCO (Leave-One-Covariate-Out)
result More reliably recovers informative features than existing methods
ExKMC improves explainable k-means clustering by balancing accuracy and simplicity.
problem Limited explainable methods for unsupervised learning.
method Develops ExKMC, a new algorithm that uses a decision tree with k′ leaves to explain k-means clustering, trading explainability for accuracy. result ExKMC produces a low-cost clustering that outperforms existing methods.
State-of-the-art clustering algorithms use heuristics to partition the feature space and provide little insight into the rationale for cluster membership, limiting their interpretability. In healthcare applications, the latter poses a barrier to the adoption of these methods since medical researchers are required to pr…
We present the Bayesian Case Model (BCM), a general framework for Bayesian case-based reasoning (CBR) and prototype classification and clustering. BCM brings the intuitive power of CBR to a Bayesian generative framework. The BCM learns prototypes, the "quintessential" observations that best represent clusters in a data…
This paper uses the relationship between graph conductance and spectral clustering to study (i) the failures of spectral clustering and (ii) the benefits of regularization. The explanation is simple. Sparse and stochastic graphs create a lot of small trees that are connected to the core of the graph by only one edge. G…
Interpretable ML methods for better decision-making with explanations.
problem Lack of transparency in black-box ML models.
method Use of Formal Concept Analysis and cooperative game theory to assess attribute importance and reduce attribute count.
result Developed methods to assess attribute importance and reduce attribute count in ML models.
Existing works on "black-box" model interpretation use local-linear approximations to explain the predictions made for each data instance in terms of the importance assigned to the different features for arriving at the prediction. These works provide instancewise explanations and thus give a local view of the model. T…
K-means fails in high dimensions with noise and few samples.
problem Clustering in high-dimensional data with noise and limited samples.
method Simple Gaussian Mixture Model (GMM) analysis.
result Almost every partition becomes a fixed point of k-means in high dimensions.
Improves hierarchical clustering in Euclidean space using autoencoders.
problem Lack of unsupervised methods for learning hierarchical structure in Euclidean space.
method Variational autoencoder with Gaussian mixture prior, rescaling latent space, and Ward's linkage.
result Improved dendrogram purity and Moseley-Wang cost function results.
K-means fails catastrophically in high dimensions, Hartigan's avoids it.
problem K-means algorithm's failure in high-dimensional data.
method Proof of k-means failure and Hartigan's algorithm success.
result Hartigan's algorithm avoids the catastrophic failure of k-means in high dimensions.
New method discovers concepts in hidden feature layers using sparse subspace clustering.
problem Local attribution methods fail to identify coherent model behavior across samples.
method Sparse Subspace Clustering (SSCC) for concept discovery.
result Empirically validated method for various image classification tasks.
A new method captures higher-order interactions in data clusters.
problem Accurately characterizing complex higher-order variable interactions.
method Local Correlation Explanation (CorEx) method: clustering and total correlation.
result Captures higher-order interactions at a local scale.
Abstraction plays a key role in concept learning and knowledge discovery; this paper is concerned with computational abstraction. In particular, we study the nature of abstraction through a group-theoretic approach, formalizing it as symmetry-driven---as opposed to data-driven---hierarchical clustering. Thus, the resul…
BiLRP explains deep similarity models by decomposing scores into feature contributions.
problem Verifying meaningful patterns in complex similarity models.
method Augmenting similarity scores with feature explanations using LRP.
result BiLRP robustly explains deep neural network features and historical document similarities.
Due to the complexity of cancer, clustering algorithms have been used to disentangle the observed heterogeneity and identify cancer subtypes that can be treated specifically. While kernel based clustering approaches allow the use of more than one input matrix, which is an important factor when considering a multidimens…
New method converts LVAs into linear projections for better understanding of complex models.
problem Limited interpretability of nonlinear machine learning models.
method Animated linear projections and radial tours.
result Improved understanding of variable importance in complex models.
The paper reveals how clustering in ReLU networks enhances interpretability.
problem Improving interpretability of deep learning models.
method Clustering of ReLU neuron patterns to reveal underlying affine maps.
result The network's predictions can be explained by feature importance within clusters.
This paper automates mining of COVID-19 scholarly articles using machine learning.
problem Time-consuming and impractical manual extraction of relevant COVID-19 research articles.
method Used machine learning approaches, specifically clustering and parallel one-class support vector machines (OCSVMs), on the CORD-19 dataset.
result Parallel OCSVMs outperform other methods for both original and reduced feature space.
The interaction between transitivity and sparsity, two common features in empirical networks, implies that there are local regions of large sparse networks that are dense. We call this the blessing of transitivity and it has consequences for both modeling and inference. Extant research suggests that statistical inferen…
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
Graph learning categorizes DeFi services into similar functionalities.
problem Identifying similar financial services in decentralized finance protocols.
method Graph representation learning (GRL) to categorize smart contract blocks into clusters.
result Purity of clustering reaches .888 in the best-case scenario.
Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not individualized for each prediction. Here we show that popular feature attribution methods are inconsistent, meaning they can lower a featur…
We study the spaces of polynomials stratified into the sets of polynomial with fixed number of roots inside certain semialgebraic region Ω, on its border, and at the complement to its closure. Presented approach is a generalisation, unification and development of several classical approaches to stability problems in …
COHORTNEY groups web users based on activity patterns.
problem Lack of academic discussion on cohort analysis for user behavior.
method Unsupervised non-parametric machine learning approach.
result COHORTNEY outperforms traditional methods in cohort analysis.
SHAP clustering explains model predictions by grouping similar feature contributions.
problem Lack of explainability in black-box models.
method SHAP values for feature contributions, supervised clustering of SHAP values.
result Insight into pathways leading to similar predictions.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Survey on efficient counterfactual explanations for various ML models.
problem Providing understandable explanations for machine learning predictions.
method Review and propose methods for computing counterfactual explanations.
result Efficient methods for various ML models and new methods for unconsidered models.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Efficiently computes counterfactual explanations for LVQ models.
problem Need to efficiently explain predictions of machine learning models.
method Derives convex and non-convex programs for LVQ models.
result Efficient computation of counterfactual explanations for LVQ models.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.