English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Memory replay based techniques have shown great success for continuallearning with incrementally accumulated Euclidean data. Directly applying themto continually expanding graphs, however, leads to the potential memoryexplosion problem due to the need to buffer representative nodes and theirassociated topological neighborhood structures. To this end, we systematicallyanalyze the key challenges in the memory explosion problem, and present ageneral framework, i.e., Parameter Decoupled Graph Neural Networks (PDGNNs)with Topology-aware Embedding Memory (TEM), to tackle this issue. The proposedframework not only reduces the memory space complexity from $\mathcal{O}(nd^L)$to $\mathcal{O}(n)$~\footnote{$n$: memory budget, $d$: average node degree,$L$: the radius of the GNN receptive field}, but also fully utilizes thetopological information for memory replay. Specifically, PDGNNs decoupletrainable parameters from the computation ego-subgraph via\textit{Topology-aware Embeddings} (TEs), which compress ego-subgraphs intocompact vectors (i.e., TEs) to reduce the memory consumption. Based on thisframework, we discover a unique \textit{pseudo-training effect} in continuallearning on expanding graphs and this effect motivates us to develop a novel\textit{coverage maximization sampling} strategy that can enhance theperformance with a tight memory budget. Thorough empirical studies demonstratethat, by tackling the memory explosion problem and incorporating topologicalinformation into memory replay, PDGNNs with TEM significantly outperformstate-of-the-art techniques, especially in the challenging class-incrementalsetting.

Topology-aware Embedding Memory for Learning on Expanding Graphs