Machine Learning

Papers
(The TQCC of Machine Learning is 6. 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 2021-06-01 to 2025-06-01.)
ArticleCitations
The role of mutual information in variational classifiers198
Automated imbalanced classification via layered learning124
Learning to bid and rank together in recommendation systems119
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics110
Adapting performance metrics for ordinal classification to interval scale: length matters94
Fairness seen as global sensitivity analysis92
One-Stage Tree: end-to-end tree builder and pruner90
Multimodal deep learning for cetacean distribution modeling of fin whales (Balaenoptera physalus) in the western Mediterranean Sea82
Parameter identifiability of a deep feedforward ReLU neural network75
Compositional scene modeling with global object-centric representations71
Maximum causal entropy inverse constrained reinforcement learning63
Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations59
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting54
Semantic-enhanced graph neural networks with global context representation54
Spike2CGR: an efficient method for spike sequence classification using chaos game representation53
Modelling spatiotemporal dynamics from Earth observation data with neural differential equations49
Robust reputation independence in ranking systems for multiple sensitive attributes45
A review on instance ranking problems in statistical learning42
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers42
Invariant representation learning via decoupling style and spurious features41
Masked autoencoder for multiagent trajectories35
Chinese character recognition with radical-structured stroke trees34
A flexible class of dependence-aware multi-label loss functions32
Maintaining AUC and H-measure over time32
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization32
Towards accurate knowledge transfer via target-awareness representation disentanglement31
Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimization29
Learning any memory-less discrete semantics for dynamical systems represented by logic programs29
Glacier: guided locally constrained counterfactual explanations for time series classification27
Trimming stability selection increases variable selection robustness27
Efficient private SCO for heavy-tailed data via averaged clipping27
A prompt-driven framework for multi-domain knowledge tracing25
On the usefulness of the fit-on-test view on evaluating calibration of classifiers25
Transfer learning with pre-trained conditional generative models25
Multi-label image classification with multi-layered multi-perspective dynamic semantic representation24
Optimal survival trees23
Generalization bounds for learning under graph-dependence: a survey23
Reinforcement learning for robotic manipulation using simulated locomotion demonstrations23
FairSwiRL: fair semi-supervised classification with representation learning22
Optimal transport for conditional domain matching and label shift22
Responsible model deployment via model-agnostic uncertainty learning21
GENs: generative encoding networks21
Artificial intelligence for laryngoscopy in vocal fold diseases: a review of dataset, technology, and ethics20
LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios20
Correction to: efficient generator of mathematical expressions for symbolic regression20
DIMBA: discretely masked black-box attack in single object tracking20
Aligning model outputs for class imbalanced non-IID federated learning19
Data-aware process discovery for malware detection: an empirical study19
Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events19
Progressive semantic learning for unsupervised skeleton-based action recognition18
Autoreplicative random forests with applications to missing value imputation18
SPA: A poisoning attack framework for graph neural networks through searching and pairing17
The backbone method for ultra-high dimensional sparse machine learning17
A unified framework for closed-form nonparametric regression, classification, preference and mixed problems with Skew Gaussian Processes17
Feature ranking for semi-supervised learning17
Dynamic datasets and market environments for financial reinforcement learning17
A contrastive neural disentanglement approach for query performance prediction16
Capturing the context-aware code change via dynamic control flow graph for commit message generation16
Testing exchangeability in the batch mode with e-values and Markov alternatives16
Paf-tracker: a novel pre-frame auxiliary and fusion visual tracker15
Autoencoding slow representations for semi-supervised data-efficient regression15
Reducing classifier overconfidence against adversaries through graph algorithms15
A taxonomy of weight learning methods for statistical relational learning15
Consensus–relevance kNN and covariate shift mitigation15
On the Discrepancy between Kleinberg’s Clustering Axioms and k-Means Clustering Algorithm Behavior15
Consolidated learning: a domain-specific model-free optimization strategy with validation on metaMIMIC benchmarks14
Correction to: Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations14
Multi-agent reinforcement learning for fast-timescale demand response of residential loads14
Connecting weighted automata, tensor networks and recurrent neural networks through spectral learning14
Probabilistic scoring lists for interpretable machine learning14
Conformal prediction for regression models with asymmetrically distributed errors: application to aircraft navigation during landing maneuver14
Context-aware spatio-temporal event prediction via convolutional Hawkes processes14
Learning biologically-interpretable latent representations for gene expression data14
One transformer for all time series: representing and training with time-dependent heterogeneous tabular data13
Exploiting counter-examples for active learning with partial labels13
Efficient and provable online reduced rank regression via online gradient descent13
Coresets for kernel clustering13
How to measure uncertainty in uncertainty sampling for active learning13
Unmasking deception: a topic-oriented multimodal approach to uncover false information on social media13
Correction to: Exploiting sparsity and statistical dependence in multivariate data fusion: an application to misinformation detection for high-impact events13
An in-depth review and analysis of mode collapse in generative adversarial networks13
Imbalanced gradients: a subtle cause of overestimated adversarial robustness13
Ordinal regression with explainable distance metric learning based on ordered sequences13
Event causality extraction through external event knowledge learning and polyhedral word embedding13
Constrained regret minimization for multi-criterion multi-armed bandits12
Understanding prediction discrepancies in classification12
Efficient federated unlearning under plausible deniability12
Empirical Bayes linked matrix decomposition12
A new formulation of Lipschitz constrained with functional gradient learning for GANs12
Applied machine learning to the determination of biochar hydrogen sulfide adsorption capacity12
Improving kernel online learning with a snapshot memory12
Targeted adversarial attacks on wind power forecasts12
Online AutoML: an adaptive AutoML framework for online learning12
Attacking neural machine translations via hybrid attention learning12
An interpretable sample selection framework against numerical label noise12
Forecasting short-term passenger flow via CBGC-SCI: an in-depth comparative study on Shenzhen Metro12
Understanding generalization error of SGD in nonconvex optimization11
Joint optimization of an autoencoder for clustering and embedding11
Adversarial concept drift detection under poisoning attacks for robust data stream mining11
Weighted neural tangent kernel: a generalized and improved network-induced kernel11
Transfer and share: semi-supervised learning from long-tailed data11
Large-scale pinball twin support vector machines11
$${{\mathrm {Latent}}Out}$$: an unsupervised deep anomaly detection approach exploiting latent space distribution11
Quantitative Gaussian approximation of randomly initialized deep neural networks11
NaCL: noise-robust cross-domain contrastive learning for unsupervised domain adaptation11
On the robustness of randomized classifiers to adversarial examples11
Fraud detection with natural language processing11
Robust matrix estimations meet Frank–Wolfe algorithm11
Gradient boosted trees for evolving data streams11
Testing conditional independence in supervised learning algorithms11
Scale-preserving automatic concept extraction (SPACE)11
Online binary classification from similar and dissimilar data11
Improving interpretability via regularization of neural activation sensitivity11
Byzantine-robust distributed sparse learning for M-estimation10
Troubleshooting image segmentation models with human-in-the-loop10
How to be fair? A study of label and selection bias10
Efficient fair principal component analysis10
Pruning during training by network efficacy modeling10
A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework10
Hitting the target: stopping active learning at the cost-based optimum10
Permutation-invariant linear classifiers10
Traditional and context-specific spam detection in low resource settings10
Empirical analysis of performance assessment for imbalanced classification10
Lifted model checking for relational MDPs10
Calibrated explanations for regression10
Jaccard-constrained dense subgraph discovery10
Fast linear model trees by PILOT10
Achieving adversarial robustness via sparsity9
Nrat: towards adversarial training with inherent label noise9
Hierarchically structured task-agnostic continual learning9
Online learning of network bottlenecks via minimax paths9
Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework9
On the benefits of representation regularization in invariance based domain generalization9
Correction to: Extracting automata from recurrent neural networks using queries and counterexamples (extended version)9
Distilling ensemble of explanations for weakly-supervised pre-training of image segmentation models9
InfoGram and admissible machine learning9
Learning answer set programs with aggregates via sampling and genetic programming9
A deep learning approach using natural language processing and time-series forecasting towards enhanced food safety9
Correction to: A neural meta-model for predicting winter wheat crop yield9
Semi-supervised Latent Block Model with pairwise constraints9
iSOUP-SymRF: Symbolic feature ranking with random forests in online multi-target regression and multi-label classification8
Federated learning with superquantile aggregation for heterogeneous data8
Wasserstein dropout8
DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network8
Generalized vec trick for fast learning of pairwise kernel models8
A deep reinforcement learning framework for continuous intraday market bidding8
Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics8
DEFT: distilling entangled factors by preventing information diffusion8
Explaining short text classification with diverse synthetic exemplars and counter-exemplars8
Cost-sensitive classification with cost uncertainty: do we need surrogate losses?8
Understanding transfer learning and gradient-based meta-learning techniques8
Time-aware tensor decomposition for sparse tensors8
Graph spring neural ODEs for link sign prediction8
On metafeatures’ ability of implicit concept identification8
Distribution-free conformal joint prediction regions for neural marked temporal point processes8
Information bottleneck and selective noise supervision for zero-shot learning8
Diverse and consistent multi-view networks for semi-supervised regression8
CoMadOut—a robust outlier detection algorithm based on CoMAD8
Polynomial-based graph convolutional neural networks for graph classification8
Explaining recommendation system using counterfactual textual explanations8
Relational data embeddings for feature enrichment with background information8
A unified framework for online trip destination prediction8
Hellinger distance decision trees for PU learning in imbalanced data sets7
A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning7
Addressing data dependency in neural networks: introducing the Knowledge Enhanced Neural Network (KENN) for time series forecasting +7
Learning to rank anomalies: scalar performance criteria and maximization of rank statistics7
Generalizing universal adversarial perturbations for deep neural networks7
Adaptive adapter routing for long-tailed class-incremental learning7
In-game soccer outcome prediction with offline reinforcement learning7
Stress detection with encoding physiological signals and convolutional neural network7
Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders7
The class imbalance problem in deep learning7
Black-box Bayesian adversarial attack with transferable priors7
A parameter-less algorithm for tensor co-clustering7
Unified convergence analysis for adaptive optimization with moving average estimator7
ShuttleFlow: learning the distribution of subsequent badminton shots using normalizing flows7
Temporal ensemble of multiple patterns’ instances for continuous prediction of events7
Gradient descent fails to learn high-frequency functions and modular arithmetic7
ROSE: robust online self-adjusting ensemble for continual learning on imbalanced drifting data streams7
Dense subgraphs induced by edge labels7
A framework for training larger networks for deep Reinforcement learning7
Spatiotemporal-view member preference contrastive representation learning for group recommendation7
Estimation of multidimensional item response theory models with correlated latent variables using variational autoencoders7
Sanitized clustering against confounding bias7
Meta-interpretive learning as metarule specialisation6
Sandbox: safeguarded multi-label learning through safe optimal transport6
Automotive fault nowcasting with machine learning and natural language processing6
A systematic approach for learning imbalanced data: enhancing zero-inflated models through boosting6
Multi-target prediction for dummies using two-branch neural networks6
MLife: a lite framework for machine learning lifecycle initialization6
Pairwise learning to rank by neural networks revisited: reconstruction, theoretical analysis and practical performance6
Towards efficient pareto-optimal utility-fairness between groups in repeated rankings6
Dynamic weighted ensemble for diarrhoea incidence predictions6
A stochastic approach to handle resource constraints as knapsack problems in ensemble pruning6
A new adaptive gradient method with gradient decomposition6
A generalized Weisfeiler-Lehman graph kernel6
Variable selection for both outcomes and predictors: sparse multivariate principal covariates regression6
When are they coming? Understanding and forecasting the timeline of arrivals at the FC Barcelona stadium on match days6
State-novelty guided action persistence in deep reinforcement learning6
Recurrent segmentation meets block models in temporal networks6
Bayesian mixture variational autoencoders for multi-modal learning6
Towards enabling learnware to handle heterogeneous feature spaces6
Learning with risks based on M-location6
Tight mixed-integer optimization formulations for prescriptive trees6
Ranking-preserved generative label enhancement6
Improve generated adversarial imitation learning with reward variance regularization6
Tree-based dynamic classifier chains6
Learning an adaptive forwarding strategy for mobile wireless networks: resource usage vs. latency6
Gradient-based causal discovery with latent variables6
A comparison of latent space modeling techniques in a plain-vanilla autoencoder setting6
0.18400692939758