Microsoft

Consistent Nonparametric Estimation for Heavy-tailed Sparse Graphs

We study graphons as a non-parametric generalization of stochastic block models, and show how to obtain compactly represented estimators for sparse networks in this framework. Our algorithms and ...
IEEE

Spatiotemporal Factorized Graph Neural Networks for Joint Large-Scale Traffic Prediction and Online Pattern Recognition

Abstract: Exploring the network-level spatiotemporal traffic interplay through traffic pattern recognition or traffic prediction is essential for intelligent traffic systems. Prediction models ...
GitHub

XLuminA, a highly-efficient, auto-differentiating discovery framework for super-resolution microscopy

Create a new conda environment and install xluminafrom PyPI. We recommend using python=3.11: conda create -n xlumina_env python=3.11 conda activate xlumina_env pip install xlumina It should be ...
IEEE

Interpretable Graph Reservoir Computing With the Temporal Pattern Attention

Abstract: Graph reservoir computing (GraphRC) gains increasing attention by virtue of its high training efficiency. However, since GraphRC is developed without knowledge of its internal mechanism, it ...