OOIR: Observatory of International Research

Papers

(The H4-Index of Machine Learning is 27. 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 2021-10-01 to 2025-10-01.)

Article	Citations
Automated imbalanced classification via layered learning	173
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers	137
Learning to bid and rank together in recommendation systems	105
The role of mutual information in variational classifiers	89
One-Stage Tree: end-to-end tree builder and pruner	81
Parameter identifiability of a deep feedforward ReLU neural network	70
Maximum causal entropy inverse constrained reinforcement learning	69
Robust reputation independence in ranking systems for multiple sensitive attributes	68
Semantic-enhanced graph neural networks with global context representation	59
Fairness seen as global sensitivity analysis	58
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	56
Compositional scene modeling with global object-centric representations	53
Modelling spatiotemporal dynamics from Earth observation data with neural differential equations	39
A review on instance ranking problems in statistical learning	37
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting	35
Adapting performance metrics for ordinal classification to interval scale: length matters	34
Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations	34
Spike2CGR: an efficient method for spike sequence classification using chaos game representation	31
Masked autoencoder for multiagent trajectories	30
Towards accurate knowledge transfer via target-awareness representation disentanglement	30
Chinese character recognition with radical-structured stroke trees	29
LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios	29
Maintaining AUC and H-measure over time	29
Learning any memory-less discrete semantics for dynamical systems represented by logic programs	29
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization	29

Responsible model deployment via model-agnostic uncertainty learning	28
Reinforcement learning for robotic manipulation using simulated locomotion demonstrations	28
On the usefulness of the fit-on-test view on evaluating calibration of classifiers	27