AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learning

arXiv:2512.18295v2 Announce Type: replace-cross Abstract: Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge. Existing methods particularly those based on experience replay typically store and revisit past graph data to mitigate catastrophic forgetting. However, these approaches pose significant limitations, including privacy concerns, inefficiency. In this work, we propose AL GNN, a novel framework for continual graph learning that eliminates the need for backpropaga

Source: arXiv cs.AI — read the full report at the original publisher.

This is a curated wire item. The Continuum Brief does not republish full third-party articles; this entry links to the original source.