Visual features extracted from rendered subgraph images consistently improve message-passing link predictors on seven benchmarks, and an efficient node-centered variant scales to large graphs.
Structure-aware transformer for graph representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
Visual features extracted from rendered subgraph images consistently improve message-passing link predictors on seven benchmarks, and an efficient node-centered variant scales to large graphs.