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 2021-05-01 to 2025-05-01.)

Article	Citations
The role of mutual information in variational classifiers	189
Automated imbalanced classification via layered learning	113
Modelling spatiotemporal dynamics from Earth observation data with neural differential equations	113
Learning to bid and rank together in recommendation systems	104
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	90
Adapting performance metrics for ordinal classification to interval scale: length matters	89
Robust reputation independence in ranking systems for multiple sensitive attributes	79
Fairness seen as global sensitivity analysis	72
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers	72
One-Stage Tree: end-to-end tree builder and pruner	70
Multimodal deep learning for cetacean distribution modeling of fin whales (Balaenoptera physalus) in the western Mediterranean Sea	60
Compositional scene modeling with global object-centric representations	51
Parameter identifiability of a deep feedforward ReLU neural network	51
Maximum causal entropy inverse constrained reinforcement learning	50
Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives	50
Spike2CGR: an efficient method for spike sequence classification using chaos game representation	47
Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations	43
A review on instance ranking problems in statistical learning	42
Semantic-enhanced graph neural networks with global context representation	41
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting	40
Invariant representation learning via decoupling style and spurious features	39
Masked autoencoder for multiagent trajectories	34
LaMMOn: language model combined graph neural network for multi-target multi-camera tracking in online scenarios	33
Optimal survival trees	31
Reinforcement learning for robotic manipulation using simulated locomotion demonstrations	30

GENs: generative encoding networks	30
Importance sampling in reinforcement learning with an estimated behavior policy	29
FairSwiRL: fair semi-supervised classification with representation learning	28
Chinese character recognition with radical-structured stroke trees	28