REVIEW 3 cited by
On Node Features for Graph Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-attributed graphs. Our experimental results show that the artificial features are highly competitive with real features.
Forward citations
Cited by 3 Pith papers
-
GNN Applied to Ego-nets for Friend Suggestions
WalkGNN, a pair-state graph neural network run on ego-nets, is reported to outperform baselines for VK friend suggestions offline and lift friend-request CTR by 12 percent online.
-
A graph neural network based on feature network for identifying influential nodes
FNGCN selects local centralities via a correlation-based feature network and uses them as GCN features, matching or slightly beating baselines on most but not all of six networks.
-
Understanding Graph Databases: A Comprehensive Tutorial and Survey
A tutorial and survey of graph databases and graph algorithms that compiles existing material but contains several incorrect code outputs.
Discussion (0). Continue with ORCID to comment.