3 papers
cs.LG2025
HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling
Thomas Bailie, Yun Sing Koh, Karthik Mukkavilli
Graphs model latent variable relationships in many real-world systems, and Message Passing Neural Networks (MPNNs) are widely used to learn such structures for downstream tasks. Wh…
cs.LG2025
Hierarchical Graph Networks for Accurate Weather Forecasting via Lightweight Training
Thomas Bailie, S. Karthik Mukkavilli, Varvara Vetrova +1
Climate events arise from intricate, multivariate dynamics governed by global-scale drivers, profoundly impacting food, energy, and infrastructure. Yet, accurate weather prediction…
cs.LG2025
Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks
Thomas Bailie, Yun Sing Koh, S. Karthik Mukkavilli +1
Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables v…