OOIR: Observatory of International Research

Papers

(The H4-Index of Machine Learning is 28. 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.)

Article	Citations
Lifted model checking for relational MDPs	295
PT4Rec: a universal prompt-tuning framework for graph contrastive learning-based recommendations	184
Schema-tune: noise-driven bias mitigation in transformer-based language models	109
Robust query performance prediction for dense retrievers via adaptive disturbance generation	99
Interpretable optimisation-based approach for hyper-box classification	97
Sparse and smooth additive isotonic model in high-dimensional settings	86
Theoretical guarantees for domain adaptation with hierarchical optimal transport	84
Minimum discrepancy principle strategy for choosing k in k-NN regression	70
Tackle balancing constraints in semi-supervised ordinal regression	69
SA-LfV: self-annotated labeling from videos for object detection	67
Learning multi-axis representation in frequency domain for medical image segmentation	66
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	58
PerfoRank: cluster-based performance ranking for improved performance evaluation and estimation in professional cycling	58
Misclassification bounds for PAC-Bayesian sparse deep learning	50
Dealing with the unevenness: deeper insights in graph-based attack and defense	49
Moreau-Yoshida variational transport: a general framework for solving regularized distributional optimization problems	47
Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio	47
Non-technical losses detection in energy consumption focusing on energy recovery and explainability	44
Bandit algorithms to personalize educational chatbots	42
Spike2CGR: an efficient method for spike sequence classification using chaos game representation	40
Assessing machine learning and data imputation approaches to handle the issue of data sparsity in sports forecasting	39
Correction to: Deep negative correlation classification	39
De-biased two-sample U-statistics with application to conditional distribution testing	35
Adapting performance metrics for ordinal classification to interval scale: length matters	33
Efficient fair principal component analysis	31

A deep learning approach using natural language processing and time-series forecasting towards enhanced food safety	30
Explainable online ensemble of deep neural network pruning for time series forecasting	28
PAC-learning with approximate predictors	28
Are LSTMs good few-shot learners?	28