Orthogonal unlearning updates plus server-side virtual clients enable effective user data removal in graph federated learning without major performance loss.
A survey on spectral graph neural networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4representative citing papers
SPECTRA improves molecular property regression on underrepresented targets via spectral graph generation with rarity-aware budgeting and Laplacian interpolation, paired with edge-aware Chebyshev GNNs, yielding competitive benchmark performance at lower compute cost.
FC-GSSL is a graph self-supervised method that corrupts nodes/edges with high low-frequency contribution and reconstructs low-frequency/general targets, improving node and graph prediction on most tested benchmarks.
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.
citing papers explorer
-
Graph Federated Unlearning for Privacy Preservation
Orthogonal unlearning updates plus server-side virtual clients enable effective user data removal in graph federated learning without major performance loss.
-
SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
SPECTRA improves molecular property regression on underrepresented targets via spectral graph generation with rarity-aware budgeting and Laplacian interpolation, paired with edge-aware Chebyshev GNNs, yielding competitive benchmark performance at lower compute cost.
-
Frequency-Corrupt Based Graph Self-Supervised Learning
FC-GSSL is a graph self-supervised method that corrupts nodes/edges with high low-frequency contribution and reconstructs low-frequency/general targets, improving node and graph prediction on most tested benchmarks.
-
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.