Topology-aware Embedding Memory for Continual Learning on Expanding Networks

arXiv:2401.13200v2 Announce Type: replace
Abstract: Memory replay based techniques have shown great success for continual learning with incrementally accumulated Euclidean data. Directly applying them to continually expanding networks, however, leads to the potential memory explosion problem due to the need to buffer representative nodes and their associated topological neighborhood structures. To this end, we systematically analyze the key challenges in the memory explosion problem, and present a general framework, i.e., Parameter Decoupled Graph Neural Networks (PDGNNs) with Topology-aware Embedding Memory …

abstract arxiv continual cs.lg data embedding leads memory networks nodes success them topology type