Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models

Documenti analoghi

• Gated Graph Attention Networks with Learnable Temperature
  di: Ma, Zhongtian, et al.
  Pubblicazione: (2026)
• Misclassification Rate and Privacy-Utility Trade-offs in Graph Convolutional Networks via Subsampling Stability
  di: Zhang, Yexin, et al.
  Pubblicazione: (2026)
• Community Detection in the Multi-View Stochastic Block Model
  di: Zhang, Yexin, et al.
  Pubblicazione: (2024)
• Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms
  di: Ma, Zhongtian, et al.
  Pubblicazione: (2024)
• Is Graph Convolution Always Beneficial For Every Feature?
  di: Zheng, Yilun, et al.
  Pubblicazione: (2024)