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 convolutional networks (GCNs) have achieved huge success in severalmachine learning (ML) tasks on graph-structured data. Recently, severalsampling techniques have been proposed for the efficient training of GCNs andto improve the performance of GCNs on ML tasks. Specifically, thesubgraph-based sampling approaches such as ClusterGCN and GraphSAINT haveachieved state-of-the-art performance on the node classification tasks. Thesesubgraph-based sampling approaches rely on heuristics -- such as graphpartitioning via edge cuts -- to identify clusters that are then treated asminibatches during GCN training. In this work, we hypothesize that rather thanrelying on such heuristics, one can learn a reinforcement learning (RL) policyto compute efficient clusters that lead to effective GCN performance. To thatend, we propose PolicyClusterGCN, an online RL framework that can identify goodclusters for GCN training. We develop a novel Markov Decision Process (MDP)formulation that allows the policy network to predict ``importance" weights onthe edges which are then utilized by a clustering algorithm (Graclus) tocompute the clusters. We train the policy network using a standard policygradient algorithm where the rewards are computed from the classificationaccuracies while training GCN using clusters given by the policy. Experimentson six real-world datasets and several synthetic datasets show thatPolicyClusterGCN outperforms existing state-of-the-art models on nodeclassification task.

PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks