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

Graph neural networks (GNNs) have found extensive applications in learningfrom graph data. However, real-world graphs often possess diverse structuresand comprise nodes and edges of varying types. To bolster the generalizationcapacity of GNNs, it has become customary to augment training graph structuresthrough techniques like graph augmentations and large-scale pre-training on awider array of graphs. Balancing this diversity while avoiding increasedcomputational costs and the notorious trainability issues of GNNs is crucial.This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with theaim of augmenting their capacity to adapt to a diverse range of training graphstructures, without incurring explosive computational overhead. The proposedGraph Mixture of Experts (GMoE) model empowers individual nodes in the graph todynamically and adaptively select more general information aggregation experts.These experts are trained to capture distinct subgroups of graph structures andto incorporate information with varying hop sizes, where those with larger hopsizes specialize in gathering information over longer distances. Theeffectiveness of GMoE is validated through a series of experiments on a diverseset of tasks, including graph, node, and link prediction, using the OGBbenchmark. Notably, it enhances ROC-AUC by $1.81\%$ in ogbg-molhiv and by$1.40\%$ in ogbg-molbbbp, when compared to the non-MoE baselines. Our code ispublicly available at https://github.com/VITA-Group/Graph-Mixture-of-Experts.

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling