RAwR augments graphs with role-aware quotient graphs from approximate equitable partitions to accelerate long-range communication in GNNs, achieving SOTA results on homophilic, heterophilic, and long-range benchmarks while recovering master-node rewiring in the limit.
arXiv preprint arXiv:2002.05287 (2020)
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
Message passing trivializes positive sample maximization in GCL via Dirichlet energy smoothing; SPGCL mitigates this by propagating only high-energy features and using low-energy ones for positive sampling.
NEM-GNN proposes a scalable DAC/ADC-less PIM architecture for GNNs with early termination and CAR execution, claiming 80-230x performance and 850-1134x energy gains over prior accelerators.
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.
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.
citing papers explorer
-
RAwR: Role-Aware Rewiring via Approximate Equitable Partition
RAwR augments graphs with role-aware quotient graphs from approximate equitable partitions to accelerate long-range communication in GNNs, achieving SOTA results on homophilic, heterophilic, and long-range benchmarks while recovering master-node rewiring in the limit.
-
Graph Navier Stokes Networks
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
-
PLACE: Prompt Learning for Attributed Community Search in Large Graphs
PLACE is a prompt-augmented graph framework for attributed community search that integrates learnable tokens with GNNs via alternating training and divide-and-conquer scaling, achieving 22% higher average F1 scores than prior methods on nine real-world graphs.
-
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
Message passing trivializes positive sample maximization in GCL via Dirichlet energy smoothing; SPGCL mitigates this by propagating only high-energy features and using low-energy ones for positive sampling.
-
A complete discussion on fully reconfigurable, digital, scalable, graph and sparsity-aware near-memory accelerator for graph neural networks
NEM-GNN proposes a scalable DAC/ADC-less PIM architecture for GNNs with early termination and CAR execution, claiming 80-230x performance and 850-1134x energy gains over prior accelerators.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.
-
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.