MGCN-FLC improves multi-view GCN node classification by using granular-ball topology construction, inter-feature enhancement, and interactive cross-view fusion to exploit three forms of consistency.
Graph classification via reference distribution learning: theory and practice.Advances in Neural Information Processing Systems, 37:137698–137740, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion
MGCN-FLC improves multi-view GCN node classification by using granular-ball topology construction, inter-feature enhancement, and interactive cross-view fusion to exploit three forms of consistency.