GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Importantly, the proposed technique offers the same linear computational complexity and constant learning complexity as classical CNNs, while being universal to any graph structure. Experiments on MNIST and 20NEWS demonstrate the ability of this novel deep learning system to learn local, stationary, and compositional features on graphs.
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
A GCN-GAE model learns node embeddings from directed weighted microservice graphs to flag anomalies via cosine similarity between load-test and live-event representations, with a synthetic injection framework reporting 96% precision.
citing papers explorer
-
GravityGraphSAGE: Link Prediction in Directed Attributed Graphs
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
-
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.
-
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.
-
E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features
E-PCN reaches 94.67% macro-accuracy on 10-class jet tagging by weighting graphs with angular separation, transverse momentum, momentum fraction, and invariant mass, with Grad-CAM showing the first two account for 76% of decisions and yielding gains over baseline PCN.
-
Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
-
From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures
A GCN-GAE model learns node embeddings from directed weighted microservice graphs to flag anomalies via cosine similarity between load-test and live-event representations, with a synthetic injection framework reporting 96% precision.