Results 51 to 60 of about 110,849 (310)
Graph Neural Networks with Adaptive Readouts [PDF]
, 2022 An effective aggregation of node features into a graph-level representation via readout functions is an essential step in numerous learning tasks involving graph neural networks.
Oglic D. +4 more
core
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 +2 more
doaj +1 more source
International Journal of Computer VisionAbstract Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose a novel GNN (called Graph in Graph Neural (GIG) Network) which can process ...
Jiongshu Wang +4 more
openaire +2 more sources
CoRR, 2019 Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data.
Zhen Zhang 0008 +2 more
openaire +3 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 +3 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 +2 more
doaj +1 more source
Symbolic Hyperdimensional Vectors with Sparse Graph Convolutional Neural Networks
, 2022 In this paper, we propose a novel way of representing graphs for processing in Graph Neural Networks. We reduce the dimensionality of the input data by using Random Indexing, a Vector Symbolic Architectural framework; we implement a new trainable neural ...
Karlgren, Jussi, +3 more
core +1 more source
Clenshaw Graph Neural Networks
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023 Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations. Recent GCN models use various residual connection techniques to alleviate the model degradation problem such as over-smoothing and gradient vanishing.
Yuhe Guo, Zhewei Wei
openaire +2 more sources
Proceedings of the AAAI Conference on Artificial Intelligence, 2022 Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invariant local aggregation of neighbors to learn a representation for each node. However, they fail to generalize to heterophilic graphs, where most neighboring nodes have different
Tianmeng Yang +5 more
openaire +2 more sources
Path integral based convolution and pooling for graph neural networks [PDF]
, 2020 Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success.
Lio P. +4 more
core