Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
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…
cs.LG2026
Revisiting Node Affinity Prediction in Temporal Graphs
Or Feldman, Krishna Sri Ipsit Mantri, Moshe Eliasof +1
Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent w…
cs.LG2024
Leveraging Temporal Graph Networks Using Module Decoupling
Or Feldman, Chaim Baskin
Modern approaches for learning on dynamic graphs have adopted the use of batches instead of applying updates one by one. The use of batches allows these techniques to become helpfu…