R-SGFormer pairs GraphMoRE embeddings with SGFormer, but its own tables show the full model fails to consistently beat SGFormer or GraphMoRE baselines.
Analyzing the expressive power of graph neural networks in a spectral perspective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning
R-SGFormer pairs GraphMoRE embeddings with SGFormer, but its own tables show the full model fails to consistently beat SGFormer or GraphMoRE baselines.