Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks
cs.LG
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/siddhartha047/Scaffold
Terminology
Sources
- Shapley-Value-Based Graph Sparsification for GNN Inference
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Demystifying Graph Sparsification Algorithms in Graph Properties Preservation
- Robust and Practical Solution of Laplacian Equations by Approximate Elimination
- A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation
- Rethinking Graph Lottery Tickets: Graph Sparsity Matters
- Unifews: You Need Fewer Operations for Efficient Graph Neural Networks
- Spectral Neural Graph Sparsification
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Graph Attention Networks
- Empirical Error Estimates for Graph Sparsification
- How Powerful are Graph Neural Networks?
- GraphSAINT: Graph Sampling Based Inductive Learning Method
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks