33 papers
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines
Kenneth Martin, Simon Heilig, Asja Fischer +3
Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the availability of many alterna…
FLASH: Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networks
Or Feldman, Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb +2
Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs. However, incorporating long histories is resource-intensive. Henc…
Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
Andrea Ceni, Alessio Gravina, Claudio Gallicchio +3
The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, exi…
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Brown Zaz, Mar Gonzà lez I CatalÃ, Ferran Hernandez Caralt +2
In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on a…
Learning from Historical Activations in Graph Neural Networks
Yaniv Galron, Hadar Sinai, Haggai Maron +1
Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pool…
Preconditioned Flow Matching
Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui +3
Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions . We identify a geometric optimization bottleneck in this re…