FedGLS trains federated graph models when some clients have only node features and no graph edges, by distilling structure knowledge into a feature encoder and generating graphs locally on graphless clients.
Learning discrete structures for graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Graph Learning with Graphless Clients
FedGLS trains federated graph models when some clients have only node features and no graph edges, by distilling structure knowledge into a feature encoder and generating graphs locally on graphless clients.