Results 31 to 40 of about 409,466 (266)

Graph Clustering with Graph Neural Networks

, 2020
Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction. However, important unsupervised problems on graphs, such as graph clustering, have proved more resistant to advances in GNNs.
Tsitsulin, Anton, Palowitch, John, Perozzi, Bryan, Müller, Emmanuel   +3 more
openaire   +3 more sources

Locally Private Graph Neural Networks [PDF]

Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2021
Graph Neural Networks (GNNs) have demonstrated superior performance in learning node representations for various graph inference tasks. However, learning over graph data can raise privacy concerns when nodes represent people or human-related variables that involve sensitive or personal information.
Sajadmanesh, Sina, Gatica-Perez, Daniel
openaire   +2 more sources

Learning flexible representations of stochastic processes on graphs

, 2018
Graph convolutional networks adapt the architecture of convolutional neural networks to learn rich representations of data supported on arbitrary graphs by replacing the convolution operations of convolutional neural networks with graph-dependent linear ...
Balan, Radu, Bohannon, Addison, Sadler, Brian   +2 more
core   +1 more source

Two-Level Graph Neural Network [PDF]

IEEE Transactions on Neural Networks and Learning Systems
Graph Neural Networks (GNNs) are recently proposed neural network structures for the processing of graph-structured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information.
Xing Ai, Chengyu Sun, Zhihong Zhang, Edwin R. Hancock   +3 more
openaire   +5 more sources

Graph coloring with physics-inspired graph neural networks

Physical Review Research, 2022
We show how graph neural networks can be used to solve the canonical graph coloring problem. We frame graph coloring as a multiclass node classification problem and utilize an unsupervised training strategy based on the statistical physics Potts model ...
Martin J. A. Schuetz, J. Kyle Brubaker, Zhihuai Zhu, Helmut G. Katzgraber   +3 more
doaj   +1 more source

Spectrum-based deep neural networks for fraud detection

, 2017
In this paper, we focus on fraud detection on a signed graph with only a small set of labeled training data. We propose a novel framework that combines deep neural networks and spectral graph analysis. In particular, we use the node projection (called as
Li, Jun, Lu, Aidong, Wu, Xintao, Yuan, Shuhan   +3 more
core   +1 more source

Motif Graph Neural Network

IEEE Transactions on Neural Networks and Learning Systems
Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations.
Xuexin Chen, Ruichu Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao   +5 more
openaire   +4 more sources

The Laplacian spectrum of neural networks

Frontiers in Computational Neuroscience, 2014
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks.
Siemon ede Lange, Marcel ede Reus, Martijn eVan Den Heuvel   +2 more
doaj   +1 more source

A Survey on Graph Neural Networks for Microservice-Based Cloud Applications

Sensors, 2022
Graph neural networks (GNNs) have achieved great success in many research areas ranging from traffic to computer vision. With increased interest in cloud-native applications, GNNs are increasingly being investigated to address various challenges in ...
Hoa Xuan Nguyen, Shaoshu Zhu, Mingming Liu   +2 more
doaj   +1 more source

Graph-to-Sequence Learning using Gated Graph Neural Networks

, 2018
Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or ...
Beck, Daniel, Cohn, Trevor, Haffari, Gholamreza   +2 more
core   +1 more source