Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
hub
arXiv preprint arXiv:2005.00687 , year=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Polynomial-time max-product algorithms for exact (neuron-level) and approximate (node-level) top-K relevant walk search in GNN-LRP explanations.
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
TravelFraudBench is a new configurable benchmark for GNN-based fraud ring detection in travel networks, simulating star, clique, and chain topologies and showing GraphSAGE outperforming MLP baselines on AUC and ring recovery.
GAT uses static attention where neighbor rankings ignore the query node and thus cannot express some graph problems; GATv2 enables dynamic attention and outperforms GAT on 11 OGB and other benchmarks with equal parameters.
Message-passing algorithms compute GNN-LRP subgraph attributions in linear time w.r.t. network depth by exploiting the distributive property.
H3 is a new three-hop index that predicts physician referrals using normalized indirect pathways and outperforms heuristics and neural nets on Medicare shared-patient data in both within-period and cross-period settings.
GraphSculptor builds efficient pre-training coresets for graph self-supervised learning using combined structural and semantic diversity metrics, achieving 99.6% performance with 10% of the data.
Cerebras CS-3 achieves up to 100x speedup over CPU for SpMM and 20x for SDDMM at 90% sparsity, with performance improving for larger matrices, but becomes slower than CPU beyond 99% sparsity.
ScaleGNN uses communication-free sampling and 4D parallelism to scale mini-batch GNN training to 2048 GPUs, achieving 3.5x speedup over prior state-of-the-art on ogbn-products.
SHIRO achieves geometric mean speedups of 221.5x to 8.8x over four baselines in distributed SpMM on up to 128 GPUs by exploiting sparsity patterns and two-tier network topologies.
DGL is a graph-centric library that optimizes GNNs via generalized sparse tensor operations, transparent graph-based optimizations, and framework-neutral design, claiming superior speed and memory use over other GNN frameworks.
Contrastive FUSE learns node embeddings from partial pairwise supervision and structural signals alone by optimizing a spectral contrastive objective with a lightweight modularity approximation, yielding competitive performance and runtime gains on citation and co-purchase graphs.
citing papers explorer
-
Learning Dynamic Stability Landscapes in Synchronization Networks
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
-
Relevant Walk Search for Explaining Graph Neural Networks
Polynomial-time max-product algorithms for exact (neuron-level) and approximate (node-level) top-K relevant walk search in GNN-LRP explanations.
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networks
TravelFraudBench is a new configurable benchmark for GNN-based fraud ring detection in travel networks, simulating star, clique, and chain topologies and showing GraphSAGE outperforming MLP baselines on AUC and ring recovery.
-
How Attentive are Graph Attention Networks?
GAT uses static attention where neighbor rankings ignore the query node and thus cannot express some graph problems; GATv2 enables dynamic attention and outperforms GAT on 11 OGB and other benchmarks with equal parameters.
-
Efficient Higher-order Subgraph Attribution via Message Passing
Message-passing algorithms compute GNN-LRP subgraph attributions in linear time w.r.t. network depth by exploiting the distributive property.
-
H3: A Healthcare Three-Hop Index for Physician Referral Network Prediction
H3 is a new three-hop index that predicts physician referrals using normalized indirect pathways and outperforms heuristics and neural nets on Medicare shared-patient data in both within-period and cross-period settings.
-
GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning
GraphSculptor builds efficient pre-training coresets for graph self-supervised learning using combined structural and semantic diversity metrics, achieving 99.6% performance with 10% of the data.
-
Exploring Sparse Matrix Multiplication Kernels on the Cerebras CS-3
Cerebras CS-3 achieves up to 100x speedup over CPU for SpMM and 20x for SDDMM at 90% sparsity, with performance improving for larger matrices, but becomes slower than CPU beyond 99% sparsity.
-
Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
ScaleGNN uses communication-free sampling and 4D parallelism to scale mini-batch GNN training to 2048 GPUs, achieving 3.5x speedup over prior state-of-the-art on ogbn-products.
-
SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
SHIRO achieves geometric mean speedups of 221.5x to 8.8x over four baselines in distributed SpMM on up to 128 GPUs by exploiting sparsity patterns and two-tier network topologies.
-
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
DGL is a graph-centric library that optimizes GNNs via generalized sparse tensor operations, transparent graph-based optimizations, and framework-neutral design, claiming superior speed and memory use over other GNN frameworks.
-
Fast and Featureless Node Representation Learning with Partial Pairwise Supervision
Contrastive FUSE learns node embeddings from partial pairwise supervision and structural signals alone by optimizing a spectral contrastive objective with a lightweight modularity approximation, yielding competitive performance and runtime gains on citation and co-purchase graphs.