Locally adaptive nearest neighbors improve automated systems' performance and are easier to interpret.
problem Improving automated systems' performance and interpretability.
method Developed a method for k nearest neighbors algorithms to learn locally adaptive metrics.
result Locally adaptive metrics improve performance and are interpretable.
Study evaluates local explanation methods for time series forecasting.
problem Lack of local interpretability methods for multivariate time series forecasting.
method Proposed two novel evaluation metrics: Area Over the Perturbation Curve for Regression and Ablation Percentage Threshold.
result Comprehensive comparison of local explanation models on two datasets.
The paper introduces metrics to objectively evaluate interpretability methods.
problem Lack of objective evaluation metrics for interpretability methods.
method Proposes a set of metrics to evaluate interpretability methods along simplicity and broadness.
result Validated metrics on different benchmark tasks and showed their utility in method selection.
The paper proposes a method to calibrate metrics for better interpretability and fairness in machine learning models.
problem Machine learning metrics are biased by class priors and vary across subpopulations.
method Calibration of precision-based metrics (F1-score, AUC-PR) to make them invariant to class priors.
result Calibrated metrics improve interpretability and provide better control over model performance.
We argue that robustness of explanations---i.e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability. We introduce metrics to quantify robustness and demonstrate that current methods do not perform well according to these metrics. Finally, we propose ways that robust…
Survey on causal interpretability models for machine learning.
problem Understanding and explaining the decisions made by machine learning models.
method Comprehensive survey on causal interpretable models.
result Evaluation metrics for interpretability are discussed.
ExpO regularizes models to improve their explainability.
problem Improving the interpretability of black-box models.
method ExpO is a hybridization of regularization and post-hoc explanation systems.
result Post-hoc explanations for ExpO-regularized models have better explanation quality.
Survey on techniques to make machine learning models understandable.
problem Humans cannot understand complex machine learning model decisions.
method Survey of existing techniques to increase interpretability.
result Challenges and achievements in interpretable machine learning need further exploration.
Researchers interpret SGD using diffusion metrics for clearer geometric understanding.
problem Elusiveness of geometrical significance in stochastic gradient descent.
method Study a deterministic model with geodesics of diffusion metrics.
result Establishes parallel with General Relativity models.
Enhanced metrics improve generative model evaluation reliability.
problem Lack of reliable quality metrics for generative models.
method Introduce Clipped Density and Clipped Coverage metrics.
result Metrics prevent out-of-distribution samples from biasing quality scores.
Quantifies interpretability and trust in ML decisions.
problem Measuring the quality and trustworthiness of ML interpretability methods.
method Proposes a quantitative measure based on information transfer rate and empirical validation.
result Empirical evidence shows the proposed metric differentiates interpretability methods and improves productivity.
Regularizes black-box models to improve interpretability.
problem Improving interpretability of black-box models without sacrificing accuracy.
method Regularizes a black-box model at training time to connect model explainability, explanation system, and quality metrics.
result Substantial improvement in explanation fidelity and stability across various datasets and explanation systems, with slight accuracy trade-off.
A fast method finds interpretable counterfactual explanations using class prototypes.
problem Finding understandable counterfactual explanations for classifier predictions.
method Using class prototypes, the method speeds up and improves interpretability of counterfactual instances.
result The method significantly speeds up and improves the interpretability of counterfactual explanations.
This paper reformulates Fβ for better model performance and interpretation.
problem Optimizing model performance and interpretation using Fβ metric. method Reformulate Fβ metric to facilitate statistical distributions and dynamic penalty weights. result Better and interpretable results with a 14% boost in F1 score for IMDB data. New geometric interpretation of Amari-Cencov α-connections on probability densities.
problem Geometric interpretation of Amari-Cencov α-connections on probability densities.
method Riemannian metrics and Levi-Civita connections.
result Geodesics of α-connections are energy-minimizing curves.
This work benchmarks counterfactual methods in time series classification.
problem Lack of benchmarking studies for counterfactual methods in time series classification.
method Redesign metrics for sparsity, plausibility, and consistency; systematically benchmark 6 CF methods on 30 datasets.
result Performance of CF methods varies across metrics and models.
The paper defines metrics for evaluating disentangled representations in learning models.
problem Evaluating disentangled representations in learning models.
method Defining semantics and metrics for disentanglement learning.
result Proposed metrics correctly characterize representations learned by different methods.
NormLIME improves feature importance explanations for deep neural networks.
problem Improving local feature explanations for deep learning models.
method NormLIME aggregates local models into global and class-specific interpretations.
result NormLIME outperforms other feature importance metrics in human user studies and numerical experiments.
New interpretation of discrete conformality using polyhedral convex hulls.
problem Understanding discrete conformality in 3D.
method Epstein-Penner convex hull construction and induced metrics.
result New bijections and interpretations of discrete conformality.
This research examines anomaly detection metrics under class imbalance.
problem Challenges in interpreting evaluation metrics under class imbalance.
method Analysis of four common anomaly detection metrics (AUROC, AUPR, F1-score, MCC) under varying imbalance ratios.
result Visualisations of metric landscapes provide an intuitive view of metric preferences and stability.
Study geodesic curvature in Heisenberg group, interpreting it as distance correction.
problem Interpreting geodesic curvature in the Heisenberg group.
method Analyzing smooth horizontal curves in the Heisenberg group, interpreting curvature as distance correction.
result Geodesic curvature in Heisenberg group is the first term in distance expansion.
CAMEL enhances manifold embedding and learning with curvature metrics.
problem High-dimensional data classification, dimension reduction, and visualization.
method CAMEL uses a Riemannian manifold with curvature metrics for enhanced expressibility and interpretability.
result CAMEL outperforms state-of-the-art methods on high-dimensional datasets.
Study geodesic properties of time series data using Wasserstein metric.
problem Modeling nonlinear time series with transport-based metrics.
method Generalized Wasserstein metric and signed cumulative distribution transforms.
result Geodesic properties provide added interpretability and robustness in time series classifiers.
Method interprets LSTMs at the cell level for better understanding of their dynamics.
problem Understanding the dynamics of LSTMs at the cell level.
method A systematic pipeline for interpreting individual hidden state dynamics using response characterization methods.
result Identifies neurons with insightful dynamics and quantifies their impact on network performance.
Framework evaluates post-hoc interpretability methods in time-series classification.
problem Lack of suitable post-hoc interpretability methods for time-series classification.
method Proposes a framework with quantitative metrics to assess interpretability methods.
result Addresses several drawbacks of existing methods, including dependence on human judgement and data distribution shift.
LionForests interprets random forests for better understanding of predictions.
problem Interpreting black-box tree ensemble models like random forests.
method Combining unsupervised learning and a similarity metric to explain tree ensembles.
result LionForests provides transparent rules for interpreting random forest predictions.
The paper generalizes the moment map interpretation of scalar curvature in Kähler geometry.
problem Interpreting the variation of the Quillen metric in Kähler geometry.
method Constructing equivariant determinant line bundles and analyzing their curvature forms.
result The moment maps μj coincide with the Z-critical equations introduced by Dervan-Hallam. We obtain Ricci flat Kähler metrics on complex symmetric spaces of rank two by using an explicit asymptotic model whose geometry at infinity is interpreted in the wonderful compactification of the symmetric space. We recover the metrics of Biquard-Gauduchon in the Hermitian case and obtain in addition several new metri…
The paper generalizes a moment map interpretation of scalar curvature in Kähler geometry.
problem Interpreting scalar curvature as a moment map on the space of compatible almost complex structures.
method Constructing equivariant determinant line bundles and analyzing their curvature forms.
result The moment maps μj coincide with the Z-critical equations and generalize Fujiki's fiber integral formula. We give a moment map interpretation of some relatively balanced metrics. As an application, we extend a result of S. K. Donaldson on constant scalar curvature Kähler metrics to the case of extremal metrics. Namely, we show that a given extremal metric is the limit of some specific relatively balanced metrics. As a coro…
CAT framework improves AI medical screening fairness and reliability.
problem Imbalanced data, varying performance across cohorts, and patient-level inconsistencies in traditional metrics.
method CAT framework introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity.
result Enhanced predictive reliability, fairness, and interpretability of AI-driven medical screening models.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
FiberNet integrates geometry into machine learning for clearer classification.
problem Lack of interpretability in traditional deep learning.
method Reformulates classification as geometric optimization on fiber bundles, introducing learnable Riemannian metrics and variational prototype optimization.
result Clear geometric interpretability and efficiency in classification.
Generative models use Riemannian manifolds to improve latent space interpretation.
problem Generative models often bias latent space interpretations.
method Use Riemannian manifolds to define latent space paths that respect ambient geometry.
result Improves interpretability of learned representations for both stochastic and deterministic generators.
Algorithm identifies intended fairness constraints from expert demonstrations for fair clustering.
problem Fair clustering challenges due to incomplete fairness constraints.
method Algorithm identifies fairness metric from expert demonstrations and generates clusters.
result Algorithm identifies and generates fair clusters from limited expert demonstrations.
New kernel interprets 3D anisotropic data with rotations and improved predictions.
problem Capturing rotated anisotropy in 3D spatial fields.
method Introduces a Lie-algebraic kernel with three principal length-scales and an explicit rotation.
result Posterior recovers rotated anisotropy and improves prediction over axis-aligned kernels.
This paper studies Dirac operators on end-periodic spin manifolds of dimension at least 4. We provide a sufficient condition for such an operator to be Fredholm for a generic end-periodic metric; this condition is shown to be necessary in dimension 4. We make use of end-periodic Dirac operators to give an analytical in…
Interpretable framework evaluates structure learning methods for causal discovery from observational data.
problem Evaluation of structure learning methods under assumption violations in causal discovery.
method Six-dimensional evaluation metric (DOS) tailored for causal discovery.
result Amortized causal discovery delivers results with high proximity to the optimal solution.
New interpretation of complex hyperbolic form as Weil-Petersson form.
problem Understanding complex hyperbolic structures on moduli spaces.
method Interpreting complex hyperbolic form as a Weil-Petersson form for punctured spheres.
result Found a new equality between two symplectic forms.
Develops framework to evaluate feature attribution methods.
problem Lack of ground truth for evaluating feature attribution methods.
method Proposes a framework including a dataset and metrics.
result Certain methods produce false positive explanations.
This paper improves confidence measurement in deep metric learning models.
problem Measuring confidence in deep metric learning models is challenging.
method Approximates class distributions using Gaussian kernel smoothing and calibrates the confidence metric.
result Improves generalization and robustness of deep metric learning models.
New metrics help rebuild trust in Active Learning for industry practitioners.
problem Misalignment of objectives between research and industry in Active Learning.
method Presentation of actionable metrics to interpret AL strategies.
result Actionable metrics improve AL performance and interpretability.
We analyze disentangled representations under a causal generative process, proposing new metrics and datasets.
problem Addressing fairness and interpretability through disentangled representations with a causal perspective.
method Work under a causal generative process, proposing new metrics and datasets to study disentanglement.
result Proposed metrics capture the desiderata of disentangled causal process.
Proposes MEED framework for model interpretation.
problem Improving model interpretability and avoiding undesired characteristics.
method Adversarial Infidelity Learning (AIL) for effective feature selection.
result AIL mechanism helps learn desired conditional distribution.
The Legendre transform and its generalizations, originally found in supersymmetric sigma-models, are techniques that can be used to give constructions of hyperkahler metrics. We give a twistor space interpretation to the generalizations of the Legendre transform construction. The Atiyah-Hitchin metric on the moduli spa…
This paper interprets critical scales in persistent homology for compact metric spaces.
problem Understanding critical scales in persistent homology for general compact metric spaces.
method Analyzing local minima of the distance function and their impact on persistence.
result Each decrease in zero-dimensional persistence and increase in one-dimensional persistence is induced by local minima of the distance function.
The geometric approach to diffeomorphic image registration known as "large deformation by diffeomorphic metric mapping" (LDDMM) is based on a left action of diffeomorphisms on images, and a right-invariant metric on a diffeomorphism group, usually defined using a reproducing kernel. We explore the use of left-invariant…
ExMatrix visualizes RF models, aiding in decision understanding.
problem Lack of interpretability in complex models like RF.
method ExMatrix, a novel visualization method for RF interpretability.
result ExMatrix handles large, complex RF models and promotes interpretability.