high-dimensional-data

This paper introduces GOTabPFN, a method that combines Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to make small tabular foundation models effective for high-dimensional, low-sample-size prediction without retraining large backbones.

AdaGraph is a graph-native clustering algorithm that operates within the kNN graph topology to overcome the curse of dimensionality, validated across genomics, NLP, and materials science domains via the Structure-Centric Machine Learning paradigm.

RSNet is an open-source R package that provides a resampling-based framework for robust and interpretable network inference in high-dimensional data, supporting partial correlation networks and conditional Gaussian Bayesian networks with graphlet-based topology analysis.