A new method for estimating graphlet counts in large networks.
problem Efficiently calculating graph statistics over massive networks.
method Lifting technique for Monte Carlo sampling of graphlets.
result Provable unbiasedness and controlled variance for all graphlets.
CNN estimates graphlet counts efficiently from historic graphs.
problem Difficulty in computing exact graphlet counts due to exponential growth.
method Convolutional Neural Network (CNN) framework with preprocessing techniques.
result Substantial speedup and high accuracy in estimating graphlet counts.
Efficiently estimates graphlet statistics in large networks.
problem Limited ability to compute graphlets in massive networks.
method Unbiased estimation framework for graphlets, parallel and scalable.
result Accurate and fast estimation of graphlet statistics in billions of edges networks.
From social science to biology, numerous applications often rely on graphlets for intuitive and meaningful characterization of networks at both the global macro-level as well as the local micro-level. While graphlets have witnessed a tremendous success and impact in a variety of domains, there has yet to be a fast and …
Proposes a new stochastic graphlet embedding method for graph-based machine learning.
problem Graph-based data lacks direct compatibility with machine learning algorithms.
method Introduces high-order stochastic graphlet embedding (SGE) to map graphs into vector spaces.
result SGE efficiently parses graphs to extract high-order graphlets and measures their distribution.
Improved protein structure classification using weighted graphlets and deep neural networks.
problem Protein structure classification for function prediction.
method Developed a weighted network and graphlet-based measure, combined with a deep neural network.
result Significantly improved performance on 36 real datasets compared to existing methods.
GoT-WAVE improves temporal network alignment by 25% accuracy and 64% speed.
problem Finding conserved network regions in temporal networks.
method Using graphlet-orbit transitions (GoTs) as a dynamic node similarity measure within DynaWAVE.
result GoT-WAVE outperforms DynaWAVE in accuracy and speed on synthetic networks.
GraphPrints detects anomalies in network flow data by analyzing graphlets.
problem Detecting anomalies in network flow data.
method Representing network flow as graphs, counting graphlets, and detecting outliers.
result Initial testing shows low false positive rates and high true positive rates.
This paper proposes a hybrid CPU-GPU framework for faster graphlet computation.
problem Efficiently computing k-vertex induced subgraph statistics in large networks.
method Hybrid multi-core CPU-GPU framework, single GPU methods, and multi-GPU methods.
result 300 times faster than state-of-the-art methods.
A faster graph kernel using optical random features.
problem High computation cost of graphlet kernel due to isomorphism test.
method Kernel random features, optical random features, mean kernel metric.
result The proposed method is orders of magnitude faster with similar or better accuracy.
Enhances graph-based pattern recognition by preserving structural information.
problem Loss of structural information in graph embedding.
method Hierarchical structure construction and Stochastic Graphlet Embedding (SGE).
result Improved graph representation with robustness.
GraphMoE generates random graphs using neural networks and graphlets.
problem Learning generative models for random graphs.
method GraphMoE uses a neural network trained with graphlets and subgraph counts to match the distribution of random graphs.
result GraphMoE can generate graphs that mimic various real-world datasets and fool graph classifiers.
New method classifies protein structures using network features.
problem Efficiently predicting protein function from structural data.
method Modelled protein structures as PSNs, used graphlets and deep learning for features.
result Proposed methods outperform existing PSC approaches in accuracy.
Repelling random walks improve graph-based sampling efficiency.
problem Efficient graph-based sampling and statistical estimation.
method Induces correlations between trajectories of an ensemble of walkers on a graph, maintaining unbiasedness.
result Improves concentration of statistical estimators on graphs.
DeepGL learns hierarchical graph representations from attributed graphs.
problem Learning deep node and edge representations from large attributed graphs.
method Derives base features, learns multi-layered hierarchical graph representation, leverages previous layer outputs, supports attributed graphs, learns interpretable features, and is space-efficient.
result DeepGL learns relational functions that generalize across-networks and is effective for across-network transfer learning tasks.
Consider a linear regression model where the design matrix X has n rows and p columns. We assume (a) p is much large than n, (b) the coefficient vector beta is sparse in the sense that only a small fraction of its coordinates is nonzero, and (c) the Gram matrix G = X'X is sparse in the sense that each row has relativel…
New framework discovers roles of edges in graphs.
problem Previous work focused on node roles, this tackles edge roles.
method Generalizable framework for learning and extracting edge roles from arbitrary graphs.
result Demonstrates utility of edge roles for network analysis.
GNNS uses graph neural networks to efficiently estimate subgraph frequency distributions.
problem Efficiently calculating subgraph frequency distributions in large networks.
method Graph Neural Networks (GNNS) for sampling and estimating subgraph frequencies.
result GNNS achieves comparable accuracy with a significant speedup of three orders of magnitude.
A new method classifies vertices in hypergraphs for biological network analysis.
problem Information loss in graph models of biological systems.
method A novel kernel method on vertex- and edge-labeled hypergraphs using hypergraphlets.
result Potential to estimate missing and false positive links in protein-protein interaction networks.