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 2022-08-01 to 2026-08-01.)
ArticleCitations
The role of mutual information in variational classifiers323
Maximum causal entropy inverse constrained reinforcement learning283
Correction to: Segmentation and feature extraction-based classification of pavement damages using hybrid computer vision and machine learning approaches255
Compositional scene modeling with global object-centric representations159
Learning to bid and rank together in recommendation systems130
Evaluating line-level localization ability of learning-based code vulnerability detection models107
MultiScale Knowledge Distillation104
Parameter identifiability of a deep feedforward ReLU neural network75
Performative Prediction in the Wild: Adapting to Arbitrary Data Distribution Maps72
Spike2CGR: an efficient method for spike sequence classification using chaos game representation69
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics58
PrunePrivyTune: Accelerating Language Models with Pruning and Differentially Private Fine-Tuning57
Automated imbalanced classification via layered learning54
Semantic-enhanced graph neural networks with global context representation49
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers48
Adapting performance metrics for ordinal classification to interval scale: length matters47
Trading-Off Statistical and Computational Efficiency via W-Step Markov Decision Processes: A Policy Gradient Approach46
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting46
Differentially-private data synthetisation for efficient re-identification risk control45
GENs: generative encoding networks44
Extended UCB Policies for Multi-armed Bandit Problems40
Towards accurate knowledge transfer via target-awareness representation disentanglement39
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization39
Trimming stability selection increases variable selection robustness37
Masked autoencoder for multiagent trajectories37
Invariant representation learning via decoupling style and spurious features36
FairSwiRL: fair semi-supervised classification with representation learning35
ABANet: An Atom-Bond Attention-Enhanced Neural Network for End-to-End Retrosynthesis35
Transfer learning with pre-trained conditional generative models34
Efficient private SCO for heavy-tailed data via averaged clipping33
Select First, Transfer Later: Choosing a Proper Dataset for SRL and GNN Based Transfer Learning33
Bias Mitigation in Large Language Models for Tabular Data Classification32
ConstellationNet: Reinventing Clustering Through GNNs31
Adversarial Distribution Balancing for Counterfactual Reasoning31
Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimization30
A prompt-driven framework for multi-domain knowledge tracing29
A calibration test for evaluating set-based epistemic uncertainty representations28
Multi-label image classification with multi-layered multi-perspective dynamic semantic representation28
On the usefulness of the fit-on-test view on evaluating calibration of classifiers27
Generalization bounds for learning under graph-dependence: a survey26
Simultaneous outlier detection and elimination in hyperspectral unmixing via weighted non-negative matrix tri-factorization25
Expanding Domain Generalization Theory: Error Bound Beyond Convex Combination Assumption25
Reinforcement Learning Guided Neural Deconstruction Search for Flexible Job Scheduling24
Glacier: guided locally constrained counterfactual explanations for time series classification24
Responsible model deployment via model-agnostic uncertainty learning24
Correction: Break a Lag: Triple Exponential Moving Average for Enhanced Optimization24
Chinese character recognition with radical-structured stroke trees24
Rényi divergence in hidden Markov models23
Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events23
Autoreplicative random forests with applications to missing value imputation23
Progressive semantic learning for unsupervised skeleton-based action recognition23
LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios23
SPA: A poisoning attack framework for graph neural networks through searching and pairing22
Correction to: efficient generator of mathematical expressions for symbolic regression22
Histogram approaches for imbalanced data streams regression22
Artificial intelligence for laryngoscopy in vocal fold diseases: a review of dataset, technology, and ethics21
DeNAV: Decentralized Self-Supervised Learning with a Training Navigator21
A Robust Approach for Image Clustering with Outliers via Tensor Low-Rank Representation21
Uncertainty Quantification in Pairwise Difference Learning for Classification20
Offline reinforcement learning for learning to dispatch for job shop scheduling20
Adaptive Swarm Mesh Refinement Using Deep Reinforcement Learning with Local Rewards20
Aligning model outputs for class imbalanced non-IID federated learning20
Dynamic datasets and market environments for financial reinforcement learning20
DIMBA: discretely masked black-box attack in single object tracking20
Consolidated learning: a domain-specific model-free optimization strategy with validation on metaMIMIC benchmarks19
Testing exchangeability in the batch mode with e-values and Markov alternatives19
TFAS: zero-shot NAS for general time-series analysis with time-frequency aware scoring18
Paf-tracker: a novel pre-frame auxiliary and fusion visual tracker18
Capturing the context-aware code change via dynamic control flow graph for commit message generation18
Pdarts: projected differentiable architecture search for seismic inversion18
LEAP: Linear equations for classifier accuracy prediction under prior probability shift18
Correction to: Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations18
Probabilistic scoring lists for interpretable machine learning18
Coresets for kernel clustering17
On the Discrepancy between Kleinberg’s Clustering Axioms and k-Means Clustering Algorithm Behavior17
Autoencoding slow representations for semi-supervised data-efficient regression17
MORE-PLR: multi-output regression employed for partial label ranking17
Counterfactual ensembles for interpretable churn prediction: from real-world to privacy-preserving synthetic data17
Reducing classifier overconfidence against adversaries through graph algorithms17
A contrastive neural disentanglement approach for query performance prediction16
Attention-Enhanced Cross-Modality Alignment for Adapting Vision-Language Models16
Conformal prediction for regression models with asymmetrically distributed errors: application to aircraft navigation during landing maneuver16
Mitigating Security Risks in Large Language Models: A Full Lifecycle Perspective16
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
Adaptive differentiable trees for transparent learning on data streams15
Multi-agent reinforcement learning for fast-timescale demand response of residential loads15
Event causality extraction through external event knowledge learning and polyhedral word embedding15
GE-PEFT: Gated Expandable Parameter-Efficient Fine-Tuning for Continual Learning14
Applied machine learning to the determination of biochar hydrogen sulfide adsorption capacity14
Generating Efficiently Realistic Counterfactual Explanations14
Least-squares temporal difference with expected eligibility traces14
Online Neural Networks for Change-Point Detection14
Attacking neural machine translations via hybrid attention learning14
Mind the gap: from plausible to valid self-explanations in large language models13
Learning de-biased environment models for delivery incentive policy optimization on food delivery platforms13
Optimal Control of Fluid Restless Multi-armed Bandits: A Machine Learning Approach13
Beyond What’s Normal: Bimodal and Heaviside Alternatives to Gaussian Process Regression13
Exploiting counter-examples for active learning with partial labels13
Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains13
Online AutoML: an adaptive AutoML framework for online learning13
Correction to: Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events13
A new formulation of Lipschitz constrained with functional gradient learning for GANs13
Efficient and interpretable raw audio classification with diagonal state space models13
Empirical Bayes linked matrix decomposition13
Efficient and provable online reduced rank regression via online gradient descent12
Targeted adversarial attacks on wind power forecasts12
Achieving collective welfare in multi-agent reinforcement learning via suggestion sharing12
Understanding prediction discrepancies in classification12
Imbalanced gradients: a subtle cause of overestimated adversarial robustness12
Constrained regret minimization for multi-criterion multi-armed bandits12
Symbolic Recovery of Differential Equations: The Identifiability Problem11
Progressive Induction-Aware Optimization for LLMs Safety Under Multi-turn Jailbreaks11
Unmasking deception: a topic-oriented multimodal approach to uncover false information on social media11
Towards Adaptive and Communication-Efficient Dynamic Federated Learning11
Prevalidated Ridge Regression is a Highly-Efficient Drop-In Replacement for Logistic Regression for High-dimensional Data11
Improving interpretability via regularization of neural activation sensitivity10
Forecasting short-term passenger flow via CBGC-SCI: an in-depth comparative study on Shenzhen Metro10
Low-Rank Fully-Connected Tensor Network Learning for Tensor-on-Tensor Regression10
Panda: partially approximate newton methods for distributed minimax optimization with unbalanced dimensions10
On the robustness of randomized classifiers to adversarial examples10
Weighted neural tangent kernel: a generalized and improved network-induced kernel10
PC-MoE: memory-efficient and privacy-preserving collaborative training for Mixture-of-Experts LLMs10
Transfer and share: semi-supervised learning from long-tailed data10
An interpretable sample selection framework against numerical label noise10
Scale-preserving automatic concept extraction (SPACE)10
Fraud detection with natural language processing10
Online binary classification from similar and dissimilar data10
Enhancing Low-Degree Graph Neural Networks via Joint Training and Improved Message Passing10
Robust matrix estimations meet Frank–Wolfe algorithm10
Correction to: Modeling PU learning using probabilistic logic programming10
Empirical analysis of performance assessment for imbalanced classification10
A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework9
Inverting Non-injective Functions with Twin Neural Network Regression9
A unified view of forward and backward losses for learning from weak labels9
Pruning during training by network efficacy modeling9
Temporal Graph Network Framework for Quantifying Pass Reception Probabilities Against Defensive Structures9
Permutation-invariant linear classifiers9
NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation9
Gradient boosted trees for evolving data streams9
LLiMe: enhancing text classifier explanations with large language models9
Surface Target Detection Method Based on YOLO with Wavelet Analysis9
Relational data embeddings for feature enrichment with background information9
Calibrated explanations for regression9
Hitting the target: stopping active learning at the cost-based optimum9
Efficient federated unlearning under plausible deniability9
Jaccard-constrained dense subgraph discovery9
Ordinal Classification with Label-Dependent Loss9
Apprenticeship Learning with Prior Beliefs Using Inverse Optimization9
Forecasting the Evolution of Scientific Knowledge: A Dynamic Knowledge Graph Approach Integrating Temporal Embeddings and Large Language Models9
Fast linear model trees by PILOT9
How to be fair? A study of label and selection bias9
Learning answer set programs with aggregates via sampling and genetic programming9
Online learning of network bottlenecks via minimax paths9
Quantitative Gaussian approximation of randomly initialized deep neural networks9
Search or split: policy gradient with adaptive policy space9
Low-Light Scene Text Image Enhancement in the Wild8
Efficient quantification on large-scale networks8
Wasserstein dropout8
Explaining recommendation system using counterfactual textual explanations8
S2TE: Staged Scale-Free Topology Evolution for Sparse Spiking Neural Networks8
Diverse and consistent multi-view networks for semi-supervised regression8
When Redundancy Matters: Machine Teaching of Representations8
Smoothing the Edges: Smooth Optimization for Sparse Regularization Using Hadamard Overparametrization8
DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network8
Correction to: A neural meta-model for predicting winter wheat crop yield8
Understanding transfer learning and gradient-based meta-learning techniques8
Nrat: towards adversarial training with inherent label noise8
Adaptive collaborative minority oversampling for multi-class imbalanced classification8
Distribution-free conformal joint prediction regions for neural marked temporal point processes8
DISTFormer: Enhance 3D Human Pose Estimation via Dual Inverse-Order Spatial-Temporal Transformer8
Graph spring neural ODEs for link sign prediction8
Geometric-k-means: a bound free approach to fast and eco-friendly k-means8
Correction to: Extracting automata from recurrent neural networks using queries and counterexamples (extended version)8
Federated learning with superquantile aggregation for heterogeneous data8
iSOUP-SymRF: Symbolic feature ranking with random forests in online multi-target regression and multi-label classification8
Information bottleneck and selective noise supervision for zero-shot learning8
Monotone Composite Quantile Regression via Second-Order Gradient Boosting Framework7
Generalizing universal adversarial perturbations for deep neural networks7
Mechanistic Interpretability of ReLU Neural Networks Through Piecewise-Affine Mapping7
Temporal ensemble of multiple patterns’ instances for continuous prediction of events7
Gradient descent fails to learn high-frequency functions and modular arithmetic7
On metafeatures’ ability of implicit concept identification7
Addressing data dependency in neural networks: introducing the Knowledge Enhanced Neural Network (KENN) for time series forecasting +7
ShuttleFlow: learning the distribution of subsequent badminton shots using normalizing flows7
Neural MCTS with LLM Guidance for Effective Program Synthesis on Abstraction and Reasoning Corpus7
Science-Gym: a simple testbed for AI-driven scientific discovery7
Hierarchically structured task-agnostic continual learning7
Unified convergence analysis for adaptive optimization with moving average estimator7
In-game soccer outcome prediction with offline reinforcement learning7
Stress detection with encoding physiological signals and convolutional neural network7
Dense subgraphs induced by edge labels7
Toward practical human-interpretable explanations7
Cost-sensitive classification with cost uncertainty: do we need surrogate losses?7
CoMadOut—a robust outlier detection algorithm based on CoMAD7
SafeGen: safeguarding privacy and fairness through a genetic method7
Sanitized clustering against confounding bias7
Race Strategy Reinforcement Learning: Optimising Pitstop Strategy with Emergent Tactics in Formula One7
Learning to rank anomalies: scalar performance criteria and maximization of rank statistics7
GNN-Based Spatio-Temporal Manifold Learning: An Application of Landslide Prediction7
Black-box Bayesian adversarial attack with transferable priors7
Spatiotemporal-view member preference contrastive representation learning for group recommendation7
KT-STFormer: Parallel Kinematic-Trajectory and Spatial-Temporal Fusion Transformer for 3D Human Pose Estimation7
A framework for training larger networks for deep Reinforcement learning6
Hellinger distance decision trees for PU learning in imbalanced data sets6
A comparison of latent space modeling techniques in a plain-vanilla autoencoder setting6
From Latent to Lucid: Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma6
Learning with risks based on M-location6
Pairwise learning to rank by neural networks revisited: reconstruction, theoretical analysis and practical performance6
Counterfactual Explanation Bake-Off: A Review and Experimental Evaluation for Time Series Classification6
A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting6
Towards efficient pareto-optimal utility-fairness between groups in repeated rankings6
A new adaptive gradient method with gradient decomposition6
Bridging XAI and spectral analysis to investigate the inductive biases of deep graph networks6
Ranking-preserved generative label enhancement6
A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning6
Adaptive adapter routing for long-tailed class-incremental learning6
State-novelty guided action persistence in deep reinforcement learning6
DGNet: Dynamic Graph Networks for Multivariate Time Series Prediction6
Linear Causal Discovery with Interventional Constraints6
Gradient-based causal discovery with latent variables6
DPG: a model to build feature subspace against adversarial patch attack6
Automotive fault nowcasting with machine learning and natural language processing6
Weakly Supervised Classification with Pre-Trained Models: A Robust Fine-Tuning Approach6
Sandbox: safeguarded multi-label learning through safe optimal transport6
Leveraging differentiable NAS and abstract genetic algorithms for optimizing on-mobile VSR performance6
Tight mixed-integer optimization formulations for prescriptive trees6
ALM-PU: positive and unlabeled learning with constrained optimization6
The class imbalance problem in deep learning6
Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification6
Constraint- and Score-Based Nonlinear Granger Causality Discovery with Kernels6
Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models6
GVFs in the real world: making predictions online for water treatment6
Improving text processing via adversarial low-rank adaptation6
Data-Driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems6
Learning an adaptive forwarding strategy for mobile wireless networks: resource usage vs. latency6
When are they coming? Understanding and forecasting the timeline of arrivals at the FC Barcelona stadium on match days6
Variable selection for both outcomes and predictors: sparse multivariate principal covariates regression6
Bayesian mixture variational autoencoders for multi-modal learning6
Ddog: optimizing multi-hop inference via dual-driven retrieval and reasoning path6
Recurrent segmentation meets block models in temporal networks6
Randomized Approach to Matrix Completion: Applications in Recommendation Systems and Image Inpainting5
Neural network structure simplification by assessing evolution in node weight magnitude5
Margin distribution and structural diversity guided ensemble pruning5
Source-free domain adaptation requires penalized diversity5
Heterogeneous multi-task Gaussian Cox processes5
A software architecture for verifiable and explainable classification5
Physics encoded blocks in residual neural network architectures for digital twin models5
Time series representations classroom (TSRC): a teacher-student-based framework for interpretability-enhanced unsupervised time series representation learning5
2.2676000595093