Machine Learning

Papers
(The TQCC of Machine Learning is 5. 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 2021-04-01 to 2025-04-01.)
ArticleCitations
Lifted model checking for relational MDPs295
PT4Rec: a universal prompt-tuning framework for graph contrastive learning-based recommendations184
Schema-tune: noise-driven bias mitigation in transformer-based language models109
Robust query performance prediction for dense retrievers via adaptive disturbance generation99
Interpretable optimisation-based approach for hyper-box classification97
Sparse and smooth additive isotonic model in high-dimensional settings86
Theoretical guarantees for domain adaptation with hierarchical optimal transport84
Minimum discrepancy principle strategy for choosing k in k-NN regression70
Tackle balancing constraints in semi-supervised ordinal regression69
SA-LfV: self-annotated labeling from videos for object detection67
Learning multi-axis representation in frequency domain for medical image segmentation66
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics58
PerfoRank: cluster-based performance ranking for improved performance evaluation and estimation in professional cycling58
Misclassification bounds for PAC-Bayesian sparse deep learning50
Dealing with the unevenness: deeper insights in graph-based attack and defense49
Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio47
Moreau-Yoshida variational transport: a general framework for solving regularized distributional optimization problems47
Non-technical losses detection in energy consumption focusing on energy recovery and explainability44
Bandit algorithms to personalize educational chatbots42
Spike2CGR: an efficient method for spike sequence classification using chaos game representation40
Assessing machine learning and data imputation approaches to handle the issue of data sparsity in sports forecasting39
Correction to: Deep negative correlation classification39
De-biased two-sample U-statistics with application to conditional distribution testing35
Adapting performance metrics for ordinal classification to interval scale: length matters33
Efficient fair principal component analysis31
A deep learning approach using natural language processing and time-series forecasting towards enhanced food safety30
Are LSTMs good few-shot learners?28
Explainable online ensemble of deep neural network pruning for time series forecasting28
PAC-learning with approximate predictors28
Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training27
Multiclass optimal classification trees with SVM-splits27
No regret sample selection with noisy labels26
Modelling spatiotemporal dynamics from Earth observation data with neural differential equations26
Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives26
GS2P: a generative pre-trained learning to rank model with over-parameterization for web-scale search26
Machine learning in corporate credit rating assessment using the expanded audit report24
Robust reputation independence in ranking systems for multiple sensitive attributes23
Adaptive infinite dropout for noisy and sparse data streams23
Recursive tree grammar autoencoders23
Utilising energy function and variational inference training for learning a graph neural network architecture21
MAP inference algorithms without approximation for collective graphical models on path graphs via discrete difference of convex algorithm21
Fairness seen as global sensitivity analysis21
Jaccard-constrained dense subgraph discovery21
Multi-consensus decentralized primal-dual fixed point algorithm for distributed learning20
Compositional scene modeling with global object-centric representations20
Nested barycentric coordinate system as an explicit feature map for polyhedra approximation and learning tasks19
Optimal clustering from noisy binary feedback19
Regional bias in monolingual English language models19
Can metafeatures help improve explanations of prediction models when using behavioral and textual data?19
The role of mutual information in variational classifiers18
Normalizing flow sampling with Langevin dynamics in the latent space18
Neural discovery of balance-aware polarized communities18
A new large-scale learning algorithm for generalized additive models18
Differentiable learning of matricized DNFs and its application to Boolean networks17
How to be fair? A study of label and selection bias17
A study of BERT for context-aware neural machine translation17
Troubleshooting image segmentation models with human-in-the-loop17
Subspace Adaptation Prior for Few-Shot Learning17
Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework16
Multimodal deep learning for cetacean distribution modeling of fin whales (Balaenoptera physalus) in the western Mediterranean Sea16
Pruning during training by network efficacy modeling16
Towards harnessing feature embedding for robust learning with noisy labels15
Interpreting machine-learning models in transformed feature space with an application to remote-sensing classification15
Explicit Explore, Exploit, or Escape ($$E^4$$): near-optimal safety-constrained reinforcement learning in polynomial time15
Word embeddings for retrieving tabular data from research publications15
Parameter identifiability of a deep feedforward ReLU neural network15
Permutation-invariant linear classifiers14
Manas: multi-agent neural architecture search14
Semantic-enhanced graph neural networks with global context representation14
Differentially private Riemannian optimization14
InfoGram and admissible machine learning13
AUTOMAT[R]IX: learning simple matrix pipelines13
Reinforcement learning tutor better supported lower performers in a math task13
Weighting non-IID batches for out-of-distribution detection13
SAED: self-attentive energy disaggregation13
PANACEA: a neural model ensemble for cyber-threat detection13
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers13
One-Stage Tree: end-to-end tree builder and pruner13
Towards adaptive unknown authentication for universal domain adaptation by classifier paradox13
SWoTTeD: an extension of tensor decomposition to temporal phenotyping13
On the benefits of representation regularization in invariance based domain generalization12
Learning from crowds with sparse and imbalanced annotations12
Partitioned hybrid learning of Bayesian network structures12
Fast spectral analysis for approximate nearest neighbor search12
Extracting automata from recurrent neural networks using queries and counterexamples (extended version)12
RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification12
SAMBA: safe model-based & active reinforcement learning12
Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations12
Matrix-wise $$\ell _0$$-constrained sparse nonnegative least squares11
Online learning of network bottlenecks via minimax paths11
Traditional and context-specific spam detection in low resource settings11
Positive-unlabeled classification under class-prior shift: a prior-invariant approach based on density ratio estimation11
Embed2Detect: temporally clustered embedded words for event detection in social media11
Hitting the target: stopping active learning at the cost-based optimum11
SLISEMAP: supervised dimensionality reduction through local explanations11
Achieving adversarial robustness via sparsity11
Word embeddings-based transfer learning for boosted relational dependency networks11
Riemannian block SPD coupling manifold and its application to optimal transport10
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting10
Adaptive covariate acquisition for minimizing total cost of classification10
Partially observable environment estimation with uplift inference for reinforcement learning based recommendation10
OWL2Vec*: embedding of OWL ontologies10
Machine truth serum: a surprisingly popular approach to improving ensemble methods10
On testing transitivity in online preference learning10
Automated imbalanced classification via layered learning10
Correction: Learning sample-aware threshold for semi-supervised learning10
Graph-based semi-supervised learning via improving the quality of the graph dynamically10
Smoothing policies and safe policy gradients10
Correction to: Nettop: A lightweight-network of orthogonal-plane features for image recognition10
A geometric framework for multiclass ensemble classifiers10
Online strongly convex optimization with unknown delays10
Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations10
Learning to bid and rank together in recommendation systems10
HIVE-COTE 2.0: a new meta ensemble for time series classification10
Semi-supervised Latent Block Model with pairwise constraints10
Composition of relational features with an application to explaining black-box predictors10
Enhanced route planning with calibrated uncertainty set9
Inclusion of domain-knowledge into GNNs using mode-directed inverse entailment9
Maximum causal entropy inverse constrained reinforcement learning9
Explanatory machine learning for sequential human teaching9
Online semi-supervised learning of composite event rules by combining structure and mass-based predicate similarity9
Weakly supervised change detection using guided anisotropic diffusion9
Credal ensembling in multi-class classification9
Calibrated explanations for regression9
Fully convolutional open set segmentation9
Kalt: generating adversarial explainable chinese legal texts9
ResGCN: attention-based deep residual modeling for anomaly detection on attributed networks9
Distilling ensemble of explanations for weakly-supervised pre-training of image segmentation models9
Deep Errors-in-Variables using a diffusion model9
Compression and restoration: exploring elasticity in continual test-time adaptation9
Fast linear model trees by PILOT9
Deep contrastive coordinated multi-view consistency clustering8
Correction to: A neural meta-model for predicting winter wheat crop yield8
A deep reinforcement learning framework for continuous intraday market bidding8
Optimal survival trees8
Temporal silhouette: validation of stream clustering robust to concept drift8
Correction to: Extracting automata from recurrent neural networks using queries and counterexamples (extended version)8
Neural RELAGGS8
A review on instance ranking problems in statistical learning8
Optimistic optimisation of composite objective with exponentiated update8
Commonsense knowledge enhanced event graph representation learning for script event prediction8
Glacier: guided locally constrained counterfactual explanations for time series classification8
Bounding the Rademacher complexity of Fourier neural operators8
Active model selection: A variance minimization approach8
Inductive learning of answer set programs for autonomous surgical task planning8
Guest editorial: special issue on reinforcement learning for real life8
Relational data embeddings for feature enrichment with background information8
Reconciling privacy and utility: an unscented Kalman filter-based framework for differentially private machine learning8
RADE: resource-efficient supervised anomaly detection using decision tree-based ensemble methods8
L2XGNN: learning to explain graph neural networks8
Distance metric learning for graph structured data7
A user-guided Bayesian framework for ensemble feature selection in life science applications (UBayFS)7
DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network7
iSOUP-SymRF: Symbolic feature ranking with random forests in online multi-target regression and multi-label classification7
Evaluating large language models for user stance detection on X (Twitter)7
Importance sampling in reinforcement learning with an estimated behavior policy7
DEFT: distilling entangled factors by preventing information diffusion7
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds7
Fair and green hyperparameter optimization via multi-objective and multiple information source Bayesian optimization7
Greedy structure learning from data that contain systematic missing values7
Towards accurate knowledge transfer via target-awareness representation disentanglement7
Methodology and evaluation in sports analytics: challenges, approaches, and lessons learned7
Adaptive transformer modelling of density function for nonparametric survival analysis7
Invariant representation learning via decoupling style and spurious features7
A flexible class of dependence-aware multi-label loss functions7
Optimal large-scale stochastic optimization of NDCG surrogates for deep learning7
Generalization bounds for learning under graph-dependence: a survey7
Wasserstein dropout7
Tracking treatment effect heterogeneity in evolving environments7
Communication-efficient clustered federated learning via model distance7
Nrat: towards adversarial training with inherent label noise7
Masked autoencoder for multiagent trajectories7
Uncovering temporal patterns in visualizations of high-dimensional data7
RGCVAE: relational graph conditioned variational autoencoder for molecule design7
Symbolic DNN-Tuner7
Understanding imbalanced data: XAI & interpretable ML framework6
Deep doubly robust outcome weighted learning6
Neighborhood relation-based incremental label propagation algorithm for partially labeled hybrid data6
A taxonomy for similarity metrics between Markov decision processes6
FairSwiRL: fair semi-supervised classification with representation learning6
SVRG meets AdaGrad: painless variance reduction6
Linear support vector regression with linear constraints6
Deep multimodal representation learning for generalizable person re-identification6
Explaining recommendation system using counterfactual textual explanations6
Discordance minimization-based imputation algorithms for missing values in rating data6
DynamiSE: dynamic signed network embedding for link prediction6
Information bottleneck and selective noise supervision for zero-shot learning6
Online active classification via margin-based and feature-based label queries6
Learning any memory-less discrete semantics for dynamical systems represented by logic programs6
Spatial entropy as an inductive bias for vision transformers6
Federated learning with superquantile aggregation for heterogeneous data6
Meta-classifier free negative sampling for extreme multilabel classification6
Markov chain importance sampling for minibatches6
Entity recognition based on heterogeneous graph reasoning of visual region and text candidate6
Root-finding approaches for computing conformal prediction set6
Efficient private SCO for heavy-tailed data via averaged clipping6
POMDP inference and robust solution via deep reinforcement learning: an application to railway optimal maintenance6
Diverse and consistent multi-view networks for semi-supervised regression6
Lagrangian objective function leads to improved unforeseen attack generalization6
TSFuse: automated feature construction for multiple time series data5
Limits of multi-relational graphs5
Time-aware tensor decomposition for sparse tensors5
Ensemble and continual federated learning for classification tasks5
Learning from interpretation transition using differentiable logic programming semantics5
Beyond confusion matrix: learning from multiple annotators with awareness of instance features5
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization5
Generalized vec trick for fast learning of pairwise kernel models5
Holistic deep learning5
Style spectroscope: improve interpretability and controllability through Fourier analysis5
Robustness verification of ReLU networks via quadratic programming5
Robust linear classification from limited training data5
Polynomial-based graph convolutional neural networks for graph classification5
Large scale tensor regression using kernels and variational inference5
Optimal transport for conditional domain matching and label shift5
Variance reduction on general adaptive stochastic mirror descent5
Reinforcement learning for robotic manipulation using simulated locomotion demonstrations5
Nested aggregation of experts using inducing points for approximated Gaussian process regression5
IntelligentPooling: practical Thompson sampling for mHealth5
Improving sequential latent variable models with autoregressive flows5
Hierarchically structured task-agnostic continual learning5
Coefficient tree regression: fast, accurate and interpretable predictive modeling5
SDANet: spatial deep attention-based for point cloud classification and segmentation5
GENs: generative encoding networks5
Cautious policy programming: exploiting KL regularization for monotonic policy improvement in reinforcement learning5
Meta-learning the invariant representation for domain generalization5
0.067539215087891