Machine Learning

Papers
(The median citation count of Machine Learning is 2. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2022-06-01 to 2026-06-01.)
ArticleCitations
The role of mutual information in variational classifiers291
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers251
Fairness seen as global sensitivity analysis227
Automated imbalanced classification via layered learning131
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting117
Robust reputation independence in ranking systems for multiple sensitive attributes98
Maximum causal entropy inverse constrained reinforcement learning92
Semantic-enhanced graph neural networks with global context representation75
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics63
Correction to: Segmentation and feature extraction-based classification of pavement damages using hybrid computer vision and machine learning approaches59
Compositional scene modeling with global object-centric representations57
Spike2CGR: an efficient method for spike sequence classification using chaos game representation56
Adapting performance metrics for ordinal classification to interval scale: length matters47
Evaluating line-level localization ability of learning-based code vulnerability detection models46
MultiScale Knowledge Distillation46
Parameter identifiability of a deep feedforward ReLU neural network45
Learning to bid and rank together in recommendation systems43
Performative Prediction in the Wild: Adapting to Arbitrary Data Distribution Maps43
PrunePrivyTune: Accelerating Language Models with Pruning and Differentially Private Fine-Tuning41
Differentially-private data synthetisation for efficient re-identification risk control40
GENs: generative encoding networks37
Extended UCB Policies for Multi-armed Bandit Problems37
LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios34
Expanding Domain Generalization Theory: Error Bound Beyond Convex Combination Assumption33
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization33
Masked autoencoder for multiagent trajectories33
Towards accurate knowledge transfer via target-awareness representation disentanglement33
Trimming stability selection increases variable selection robustness32
Invariant representation learning via decoupling style and spurious features30
A calibration test for evaluating set-based epistemic uncertainty representations30
Glacier: guided locally constrained counterfactual explanations for time series classification29
Multi-label image classification with multi-layered multi-perspective dynamic semantic representation29
Responsible model deployment via model-agnostic uncertainty learning29
FairSwiRL: fair semi-supervised classification with representation learning28
Select First, Transfer Later: Choosing a Proper Dataset for SRL and GNN Based Transfer Learning28
ABANet: An Atom-Bond Attention-Enhanced Neural Network for End-to-End Retrosynthesis28
Transfer learning with pre-trained conditional generative models28
Efficient private SCO for heavy-tailed data via averaged clipping27
Simultaneous outlier detection and elimination in hyperspectral unmixing via weighted non-negative matrix tri-factorization27
Bias Mitigation in Large Language Models for Tabular Data Classification25
Generalization bounds for learning under graph-dependence: a survey25
ConstellationNet: Reinventing Clustering Through GNNs24
A prompt-driven framework for multi-domain knowledge tracing24
Adversarial Distribution Balancing for Counterfactual Reasoning24
Chinese character recognition with radical-structured stroke trees24
Progressive semantic learning for unsupervised skeleton-based action recognition23
Correction: Break a Lag: Triple Exponential Moving Average for Enhanced Optimization23
Rényi divergence in hidden Markov models23
Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimization23
On the usefulness of the fit-on-test view on evaluating calibration of classifiers23
Autoreplicative random forests with applications to missing value imputation22
DIMBA: discretely masked black-box attack in single object tracking22
Artificial intelligence for laryngoscopy in vocal fold diseases: a review of dataset, technology, and ethics22
Feature ranking for semi-supervised learning21
Uncertainty Quantification in Pairwise Difference Learning for Classification21
Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events21
A Robust Approach for Image Clustering with Outliers via Tensor Low-Rank Representation20
Histogram approaches for imbalanced data streams regression20
Aligning model outputs for class imbalanced non-IID federated learning20
Correction to: efficient generator of mathematical expressions for symbolic regression20
DeNAV: Decentralized Self-Supervised Learning with a Training Navigator19
Dynamic datasets and market environments for financial reinforcement learning19
SPA: A poisoning attack framework for graph neural networks through searching and pairing19
Offline reinforcement learning for learning to dispatch for job shop scheduling19
TFAS: zero-shot NAS for general time-series analysis with time-frequency aware scoring18
Consolidated learning: a domain-specific model-free optimization strategy with validation on metaMIMIC benchmarks18
Testing exchangeability in the batch mode with e-values and Markov alternatives18
Paf-tracker: a novel pre-frame auxiliary and fusion visual tracker18
Reducing classifier overconfidence against adversaries through graph algorithms18
Probabilistic scoring lists for interpretable machine learning17
Capturing the context-aware code change via dynamic control flow graph for commit message generation17
Pdarts: projected differentiable architecture search for seismic inversion17
MORE-PLR: multi-output regression employed for partial label ranking17
LEAP: Linear equations for classifier accuracy prediction under prior probability shift17
Correction to: Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations17
Event causality extraction through external event knowledge learning and polyhedral word embedding17
A contrastive neural disentanglement approach for query performance prediction17
Adaptive differentiable trees for transparent learning on data streams17
Conformal prediction for regression models with asymmetrically distributed errors: application to aircraft navigation during landing maneuver16
Counterfactual ensembles for interpretable churn prediction: from real-world to privacy-preserving synthetic data16
Coresets for kernel clustering16
On the Discrepancy between Kleinberg’s Clustering Axioms and k-Means Clustering Algorithm Behavior16
Autoencoding slow representations for semi-supervised data-efficient regression16
Consensus–relevance kNN and covariate shift mitigation16
One transformer for all time series: representing and training with time-dependent heterogeneous tabular data16
An in-depth review and analysis of mode collapse in generative adversarial networks15
Multi-agent reinforcement learning for fast-timescale demand response of residential loads15
Mitigating Security Risks in Large Language Models: A Full Lifecycle Perspective15
Attacking neural machine translations via hybrid attention learning15
Attention-Enhanced Cross-Modality Alignment for Adapting Vision-Language Models15
Understanding prediction discrepancies in classification15
Least-squares temporal difference with expected eligibility traces14
Mind the gap: from plausible to valid self-explanations in large language models14
Learning de-biased environment models for delivery incentive policy optimization on food delivery platforms14
Beyond What’s Normal: Bimodal and Heaviside Alternatives to Gaussian Process Regression14
Correction to: Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events14
Empirical Bayes linked matrix decomposition13
Efficient and provable online reduced rank regression via online gradient descent13
Unmasking deception: a topic-oriented multimodal approach to uncover false information on social media13
Achieving collective welfare in multi-agent reinforcement learning via suggestion sharing13
Exploiting counter-examples for active learning with partial labels13
Online AutoML: an adaptive AutoML framework for online learning13
A new formulation of Lipschitz constrained with functional gradient learning for GANs13
Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains12
Applied machine learning to the determination of biochar hydrogen sulfide adsorption capacity12
Symbolic Recovery of Differential Equations: The Identifiability Problem12
Imbalanced gradients: a subtle cause of overestimated adversarial robustness12
Generating Efficiently Realistic Counterfactual Explanations12
Targeted adversarial attacks on wind power forecasts12
Optimal Control of Fluid Restless Multi-armed Bandits: A Machine Learning Approach12
Constrained regret minimization for multi-criterion multi-armed bandits12
Efficient and interpretable raw audio classification with diagonal state space models12
Search or split: policy gradient with adaptive policy space12
Online Neural Networks for Change-Point Detection12
Forecasting short-term passenger flow via CBGC-SCI: an in-depth comparative study on Shenzhen Metro11
On the robustness of randomized classifiers to adversarial examples11
Enhancing Low-Degree Graph Neural Networks via Joint Training and Improved Message Passing11
Correction to: Modeling PU learning using probabilistic logic programming11
Transfer and share: semi-supervised learning from long-tailed data11
Online binary classification from similar and dissimilar data11
An interpretable sample selection framework against numerical label noise10
Weighted neural tangent kernel: a generalized and improved network-induced kernel10
Panda: partially approximate newton methods for distributed minimax optimization with unbalanced dimensions10
Efficient federated unlearning under plausible deniability10
Scale-preserving automatic concept extraction (SPACE)10
Low-Rank Fully-Connected Tensor Network Learning for Tensor-on-Tensor Regression10
Robust matrix estimations meet Frank–Wolfe algorithm10
NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation10
Learning answer set programs with aggregates via sampling and genetic programming9
Apprenticeship Learning with Prior Beliefs Using Inverse Optimization9
Lifted model checking for relational MDPs9
Gradient boosted trees for evolving data streams9
A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework9
Fraud detection with natural language processing9
A unified view of forward and backward losses for learning from weak labels9
Jaccard-constrained dense subgraph discovery9
Online learning of network bottlenecks via minimax paths9
Quantitative Gaussian approximation of randomly initialized deep neural networks9
PC-MoE: memory-efficient and privacy-preserving collaborative training for Mixture-of-Experts LLMs9
Adversarial concept drift detection under poisoning attacks for robust data stream mining9
Hitting the target: stopping active learning at the cost-based optimum9
Traditional and context-specific spam detection in low resource settings9
Ordinal Classification with Label-Dependent Loss9
Improving interpretability via regularization of neural activation sensitivity9
Empirical analysis of performance assessment for imbalanced classification9
Permutation-invariant linear classifiers9
Temporal Graph Network Framework for Quantifying Pass Reception Probabilities Against Defensive Structures9
How to be fair? A study of label and selection bias8
iSOUP-SymRF: Symbolic feature ranking with random forests in online multi-target regression and multi-label classification8
DISTFormer: Enhance 3D Human Pose Estimation via Dual Inverse-Order Spatial-Temporal Transformer8
Adaptive collaborative minority oversampling for multi-class imbalanced classification8
SafeGen: safeguarding privacy and fairness through a genetic method8
DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network8
Correction to: Extracting automata from recurrent neural networks using queries and counterexamples (extended version)8
Graph spring neural ODEs for link sign prediction8
Calibrated explanations for regression8
Fast linear model trees by PILOT8
Low-Light Scene Text Image Enhancement in the Wild8
Distribution-free conformal joint prediction regions for neural marked temporal point processes8
Relational data embeddings for feature enrichment with background information8
When Redundancy Matters: Machine Teaching of Representations8
LLiMe: enhancing text classifier explanations with large language models8
Correction to: A neural meta-model for predicting winter wheat crop yield8
Pruning during training by network efficacy modeling8
Distilling ensemble of explanations for weakly-supervised pre-training of image segmentation models8
Diverse and consistent multi-view networks for semi-supervised regression8
Science-Gym: a simple testbed for AI-driven scientific discovery8
CoMadOut—a robust outlier detection algorithm based on CoMAD8
Wasserstein dropout8
Efficient quantification on large-scale networks8
Hierarchically structured task-agnostic continual learning8
Explaining recommendation system using counterfactual textual explanations8
On metafeatures’ ability of implicit concept identification7
Mechanistic Interpretability of ReLU Neural Networks Through Piecewise-Affine Mapping7
Gradient descent fails to learn high-frequency functions and modular arithmetic7
Addressing data dependency in neural networks: introducing the Knowledge Enhanced Neural Network (KENN) for time series forecasting +7
Monotone Composite Quantile Regression via Second-Order Gradient Boosting Framework7
Temporal ensemble of multiple patterns’ instances for continuous prediction of events7
Understanding transfer learning and gradient-based meta-learning techniques7
Geometric-k-means: a bound free approach to fast and eco-friendly k-means7
Federated learning with superquantile aggregation for heterogeneous data7
Sanitized clustering against confounding bias7
Spatiotemporal-view member preference contrastive representation learning for group recommendation7
Stress detection with encoding physiological signals and convolutional neural network7
Cost-sensitive classification with cost uncertainty: do we need surrogate losses?7
Information bottleneck and selective noise supervision for zero-shot learning7
Nrat: towards adversarial training with inherent label noise7
ALM-PU: positive and unlabeled learning with constrained optimization7
Toward practical human-interpretable explanations7
Hellinger distance decision trees for PU learning in imbalanced data sets7
A unified framework for online trip destination prediction7
Black-box Bayesian adversarial attack with transferable priors7
S2TE: Staged Scale-Free Topology Evolution for Sparse Spiking Neural Networks7
Smoothing the Edges: Smooth Optimization for Sparse Regularization Using Hadamard Overparametrization7
ShuttleFlow: learning the distribution of subsequent badminton shots using normalizing flows7
Bridging XAI and spectral analysis to investigate the inductive biases of deep graph networks6
GVFs in the real world: making predictions online for water treatment6
A new adaptive gradient method with gradient decomposition6
DGNet: Dynamic Graph Networks for Multivariate Time Series Prediction6
Improving text processing via adversarial low-rank adaptation6
Variable selection for both outcomes and predictors: sparse multivariate principal covariates regression6
Towards efficient pareto-optimal utility-fairness between groups in repeated rankings6
Leveraging differentiable NAS and abstract genetic algorithms for optimizing on-mobile VSR performance6
State-novelty guided action persistence in deep reinforcement learning6
A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting6
GNN-Based Spatio-Temporal Manifold Learning: An Application of Landslide Prediction6
Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification6
Dense subgraphs induced by edge labels6
Learning to rank anomalies: scalar performance criteria and maximization of rank statistics6
Pairwise learning to rank by neural networks revisited: reconstruction, theoretical analysis and practical performance6
DOC$$^3$$: deep one class classification using contradictions6
Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models6
Data-Driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems6
When are they coming? Understanding and forecasting the timeline of arrivals at the FC Barcelona stadium on match days6
In-game soccer outcome prediction with offline reinforcement learning6
Sandbox: safeguarded multi-label learning through safe optimal transport6
A comparison of latent space modeling techniques in a plain-vanilla autoencoder setting6
Recurrent segmentation meets block models in temporal networks6
Weakly Supervised Classification with Pre-Trained Models: A Robust Fine-Tuning Approach6
Generalizing universal adversarial perturbations for deep neural networks6
Adaptive adapter routing for long-tailed class-incremental learning6
A framework for training larger networks for deep Reinforcement learning6
Automotive fault nowcasting with machine learning and natural language processing6
Learning an adaptive forwarding strategy for mobile wireless networks: resource usage vs. latency6
Learning with risks based on M-location6
Bayesian mixture variational autoencoders for multi-modal learning6
Jensen–Tsallis divergence for supervised classification under data imbalance6
Gradient-based causal discovery with latent variables6
Ranking-preserved generative label enhancement6
Ddog: optimizing multi-hop inference via dual-driven retrieval and reasoning path6
Counterfactual Explanation Bake-Off: A Review and Experimental Evaluation for Time Series Classification6
A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning6
The class imbalance problem in deep learning6
Unified convergence analysis for adaptive optimization with moving average estimator6
Tight mixed-integer optimization formulations for prescriptive trees6
Heterogeneous multi-task Gaussian Cox processes5
Contrastive counterfactual visual explanations with overdetermination5
Drop-in efficient self-attention approximation method5
Classification with costly features in hierarchical deep sets5
Correction to: Conformal load prediction with transductive graph autoencoders5
A brain-inspired algorithm for training highly sparse neural networks5
A class sensitivity feature guided T-type generative model for noisy label classification5
Neural network structure simplification by assessing evolution in node weight magnitude5
Explaining neural networks without access to training data5
Boundary-restricted metric learning5
Margin distribution and structural diversity guided ensemble pruning5
Time series representations classroom (TSRC): a teacher-student-based framework for interpretability-enhanced unsupervised time series representation learning5
Adjusting regression models for conditional uncertainty calibration5
Explainable dating of greek papyri images5
Naive automated machine learning5
0.26080393791199