List of datasets in computer vision and image processing
Outline of machine learning
v
t
e
A graph neural network (GNN) belongs to a class of artificial neural networks for processing data that can be represented as graphs.[1][2][3][4][5]
In the more general subject of "geometric deep learning", certain existing neural network architectures can be interpreted as GNNs operating on suitably defined graphs.[6] A convolutional neural network layer, in the context of computer vision, can be seen as a GNN applied to graphs whose nodes are pixels and only adjacent pixels are connected by edges in the graph. A transformer layer, in natural language processing, can be seen as a GNN applied to complete graphs whose nodes are words or tokens in a passage of natural language text.
The key design element of GNNs is the use of pairwise message passing, such that graph nodes iteratively update their representations by exchanging information with their neighbors. Since their inception, several different GNN architectures have been proposed,[2][3][7][8][9] which implement different flavors of message passing,[6][10] started by recursive[2] or convolutional constructive[3] approaches. As of 2022[update], whether it is possible to define GNN architectures "going beyond" message passing, or if every GNN can be built on message passing over suitably defined graphs, is an open research question.[11]
Relevant application domains for GNNs include Natural Language Processing,[12] social networks,[13] citation networks,[14] molecular biology,[15] chemistry,[16][17] physics[18] and NP-hard combinatorial optimization problems.[19]
Several open source libraries implementing graph neural networks are available, such as PyTorch Geometric[20] (PyTorch), TensorFlow GNN[21] (TensorFlow), jraph[22] (Google JAX), and GraphNeuralNetworks.jl[23]/GeometricFlux.jl[24] (Julia, Flux).
^Cite error: The named reference wucuipeizhao2022 was invoked but never defined (see the help page).
^ abcCite error: The named reference scarselli2009 was invoked but never defined (see the help page).
^ abcCite error: The named reference micheli2009 was invoked but never defined (see the help page).
^Cite error: The named reference sanchez2021 was invoked but never defined (see the help page).
^Cite error: The named reference daigavane2021 was invoked but never defined (see the help page).
^ abCite error: The named reference bronstein2021 was invoked but never defined (see the help page).
^Cite error: The named reference kipf2016 was invoked but never defined (see the help page).
^Cite error: The named reference hamilton2017 was invoked but never defined (see the help page).
^Cite error: The named reference velickovic2018 was invoked but never defined (see the help page).
^Cite error: The named reference hajij2022 was invoked but never defined (see the help page).
^Cite error: The named reference velickovic2022 was invoked but never defined (see the help page).
^Cite error: The named reference wuchen2023 was invoked but never defined (see the help page).
^Cite error: The named reference ying2018 was invoked but never defined (see the help page).
^Cite error: The named reference stanforddata was invoked but never defined (see the help page).
^Zhang, Weihang; Cui, Yang; Liu, Bowen; Loza, Martin; Park, Sung-Joon; Nakai, Kenta (1 December 2023). "HyGAnno: Hybrid graph neural network-based cell type annotation for single-cell ATAC sequencing data". doi:10.1101/2023.11.29.569114. {{cite journal}}: Cite journal requires |journal= (help)
^Cite error: The named reference gilmer2017 was invoked but never defined (see the help page).
^Coley, Connor W.; Jin, Wengong; Rogers, Luke; Jamison, Timothy F.; Jaakkola, Tommi S.; Green, William H.; Barzilay, Regina; Jensen, Klavs F. (2019-01-02). "A graph-convolutional neural network model for the prediction of chemical reactivity". Chemical Science. 10 (2): 370–377. doi:10.1039/C8SC04228D. ISSN 2041-6539. PMC 6335848. PMID 30746086.
^Cite error: The named reference qasim2019 was invoked but never defined (see the help page).
^Cite error: The named reference li2018 was invoked but never defined (see the help page).
^Cite error: The named reference fey2019 was invoked but never defined (see the help page).
^Cite error: The named reference tfgnn2022 was invoked but never defined (see the help page).
^Cite error: The named reference jraph2022 was invoked but never defined (see the help page).
^Cite error: The named reference Lucibello2021GNN was invoked but never defined (see the help page).
A graphneuralnetwork (GNN) belongs to a class of artificial neuralnetworks for processing data that can be represented as graphs. In the more general...
replaced with a strictly feedforward neuralnetwork, while an infinite impulse recurrent network is a directed cyclic graph that can not be unrolled. Additional...
A recursive neuralnetwork is a kind of deep neuralnetwork created by applying the same set of weights recursively over a structured input, to produce...
neuralnetworks, marking a departure from the typical focus on learning mappings between finite-dimensional Euclidean spaces or finite sets. Neural operators...
social networks such as LinkedIn and Facebook. Recent developments in data science and machine learning, particularly in graphneuralnetworks and representation...
types of artificial neuralnetworks (ANN). Artificial neuralnetworks are computational models inspired by biological neuralnetworks, and are used to approximate...
The Open NeuralNetwork Exchange (ONNX) [ˈɒnɪks] is an open-source artificial intelligence ecosystem of technology companies and research organizations...
Weisfeiler Leman test can also be applied in the later context. Graph isomorphism Graphneuralnetwork Huang, Ningyuan; Villar, Soledad (2022), "A Short Tutorial...
methods based on neuralnetworks with representation learning. The adjective "deep" refers to the use of multiple layers in the network. Methods used can...
An artificial neuralnetwork (ANN) combines biological principles with advanced statistics to solve problems in domains such as pattern recognition and...
machine learning, a neural scaling law is a scaling law relating parameters of a family of neuralnetworks. In general, a neural model can be characterized...
that network to a different system. A neuralnetwork without memory would typically have to learn about each transit system from scratch. On graph traversal...
graphs as a representation of relations between discrete objects Network science, an academic field that studies complex networksNetworks, a graph with...
{\displaystyle a_{ij}} . A graph signal is simply a real-valued function on the set of nodes of the graph. In graphneuralnetworks, graph signals are sometimes...
representations of nodes in graphs. The algorithm is considered one of the best graph classifiers. Struc2vec GraphNeuralNetwork Grover, Aditya; Leskovec...
rock band Graphneuralnetwork, a class of neuralnetwork for processing data best represented by graph data structures Guerrilla News Network, a defunct...
Neural architecture search (NAS) is a technique for automating the design of artificial neuralnetworks (ANN), a widely used model in the field of machine...
natural language processing. Recently, it has also been introduced to graphneuralnetworks applicable to non-grid data. Transferring the knowledge from a large...
convolutional neuralnetwork structure proposed by LeCun et al. in 1998. In general, LeNet refers to LeNet-5 and is a simple convolutional neuralnetwork. Convolutional...
traditional neuralnetworks tailored for grid-like structures, TNNs are adept at handling more intricate data representations, such as graphs, simplicial...
Hopfield network (Ising model of a neuralnetwork or Ising–Lenz–Little model or Amari-Little-Hopfield network) is a spin glass system used to model neural networks...
Artificial neuralnetworks are combinations of multiple simple mathematical functions that implement more complicated functions from (typically) real-valued...
of convolution on graphs, it makes possible to adapt the conventional convolutional neuralnetworks (CNN) to work on graphs. Graph structured semi-supervised...
An efficiently updatable neuralnetwork (NNUE, a Japanese wordplay on Nue, sometimes stylised as ƎUИИ) is a neuralnetwork-based evaluation function whose...