משה אליסוף

אקדמי בכיר

FLASH

Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networks

Or Feldman, Krishna Sri Ipsit Mantri, Carola Bibiane Schönlieb, Chaim Baskin,Moshe Eliasof

Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs. However, incorporating long histories is resource-intensive. Hence, temporal graph neural networks (TGNNs) often rely on historical neighbors sampling heuristics such as uniform sampling or recent neighbors selection. These heuristics are static and fail to adapt to the underlying graph structure. We introduce FLASH, a learnable and graph-adaptive neighborhood selection mechanism that generalizes existing heuristics. FLASH integrates seamlessly into TGNNs and is trained end-to-end using a self-supervised ranking loss. We provide theoretical evidence that commonly used heuristics hinder TGNNs performance, motivating our design. Extensive experiments across multiple benchmarks demonstrate consistent and significant performance improvements for TGNNs equipped with FLASH.

שפת פרסום אנגלית
דפים 4278-4285
סטטוס פרסום פורסם - 01.01.2026

ASJC Scopus subject areas

Artificial Intelligence
גישה למסמך
10.24963/ijcai.2026/476
קבצים וקישורים אחרים
Link to publication in Scopus