Random sampling maps (with-replacement, binning, species) induce metrics that give uniform any-dimensional generalization and sketching rates for continuous functions on sequences, graphs and tensors.
The graph neural network model.IEEE Transactions on Neural Networks, 20(1):61–80
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
OgBench is the first benchmark platform for GNN graph-level prediction in the n << p omics regime and finds that common GNNs often underperform MLPs and classical baselines.
Neural networks learn to construct argumentation structures that explain classifications through support and attack relations, trained jointly with differentiable semantics and structure constraints.
GHR uses hierarchical recurrence on pooled graph abstractions to improve long-range dependency capture and out-of-range generalization while using far fewer parameters than existing models.
citing papers explorer
-
Any-Dimensional Learning by Sampling
Random sampling maps (with-replacement, binning, species) induce metrics that give uniform any-dimensional generalization and sketching rates for continuous functions on sequences, graphs and tensors.