OOIR: Observatory of International Research

Papers

(The H4-Index of Machine Learning is 32. 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 2022-08-01 to 2026-08-01.)

Article	Citations
The role of mutual information in variational classifiers	323
Maximum causal entropy inverse constrained reinforcement learning	283
Correction to: Segmentation and feature extraction-based classification of pavement damages using hybrid computer vision and machine learning approaches	255
Compositional scene modeling with global object-centric representations	159
Learning to bid and rank together in recommendation systems	130
Evaluating line-level localization ability of learning-based code vulnerability detection models	107
MultiScale Knowledge Distillation	104
Parameter identifiability of a deep feedforward ReLU neural network	75
Performative Prediction in the Wild: Adapting to Arbitrary Data Distribution Maps	72
Spike2CGR: an efficient method for spike sequence classification using chaos game representation	69
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	58
PrunePrivyTune: Accelerating Language Models with Pruning and Differentially Private Fine-Tuning	57
Automated imbalanced classification via layered learning	54
Semantic-enhanced graph neural networks with global context representation	49
Meta-learning for heterogeneous treatment effect estimation with closed-form solvers	48
Adapting performance metrics for ordinal classification to interval scale: length matters	47
SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting	46
Trading-Off Statistical and Computational Efficiency via W-Step Markov Decision Processes: A Policy Gradient Approach	46
Differentially-private data synthetisation for efficient re-identification risk control	45
GENs: generative encoding networks	44
Extended UCB Policies for Multi-armed Bandit Problems	40
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization	39
Towards accurate knowledge transfer via target-awareness representation disentanglement	39
Trimming stability selection increases variable selection robustness	37
Masked autoencoder for multiagent trajectories	37

Invariant representation learning via decoupling style and spurious features	36
FairSwiRL: fair semi-supervised classification with representation learning	35
ABANet: An Atom-Bond Attention-Enhanced Neural Network for End-to-End Retrosynthesis	35
Transfer learning with pre-trained conditional generative models	34
Efficient private SCO for heavy-tailed data via averaged clipping	33
Select First, Transfer Later: Choosing a Proper Dataset for SRL and GNN Based Transfer Learning	33
Bias Mitigation in Large Language Models for Tabular Data Classification	32