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 2021-06-01 to 2025-06-01.)

Article	Citations
The role of mutual information in variational classifiers	198
Automated imbalanced classification via layered learning	124
Learning to bid and rank together in recommendation systems	119
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	110
Adapting performance metrics for ordinal classification to interval scale: length matters	94
Fairness seen as global sensitivity analysis	92
One-Stage Tree: end-to-end tree builder and pruner	90
Multimodal deep learning for cetacean distribution modeling of fin whales (Balaenoptera physalus) in the western Mediterranean Sea	82
Parameter identifiability of a deep feedforward ReLU neural network	75
Compositional scene modeling with global object-centric representations	71
Maximum causal entropy inverse constrained reinforcement learning	63
Surrogate models of radiative transfer codes for atmospheric trace gas retrievals from satellite observations	59
Semantic-enhanced graph neural networks with global context representation	54
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting	54
Spike2CGR: an efficient method for spike sequence classification using chaos game representation	53
Modelling spatiotemporal dynamics from Earth observation data with neural differential equations	49
Robust reputation independence in ranking systems for multiple sensitive attributes	45
A review on instance ranking problems in statistical learning	42
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers	42
Invariant representation learning via decoupling style and spurious features	41
Masked autoencoder for multiagent trajectories	35
Chinese character recognition with radical-structured stroke trees	34
Maintaining AUC and H-measure over time	32
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization	32
A flexible class of dependence-aware multi-label loss functions	32

Towards accurate knowledge transfer via target-awareness representation disentanglement	31
Learning any memory-less discrete semantics for dynamical systems represented by logic programs	29
Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimization	29