Blog - page 2
Improving Graph Neural Networks via Network-in-network Architecture
By Yakun Song, in blog
As Graph Neural Networks (GNNs) has become increasingly popular, there is a wide interest of designing deeper GNN architecture. However, deep GNNs suffer from the oversmoothing issue where the learnt node representations quickly become indistinguishable with more layers. This blog features a simple yet effective technique to build a deep GNN without the concern of oversmoothing. The new architecture, Network in Graph Neural Networks (NGNN) inspired by the network-in-network architecture for computer vision, has shown superior performance on multiple Open Graph Benchmark (OGB) leaderboards.
Read more28 November
Accelerating Partitioning of Billion-scale Graphs with DGL v0.9.1
Check out how DGL v0.9.1 helps users partition graphs of billions of nodes and edges.
Read more19 September
v0.9 Release Highlights
Check out the highlighted features of the new 0.9 release!
Read more25 July