Results 41 to 50 of about 9,290 (165)

GNN-Ensemble: Towards Random Decision Graph Neural Networks

open access: yes2023 IEEE International Conference on Big Data (BigData), 2023
Graph Neural Networks (GNNs) have enjoyed wide spread applications in graph-structured data. However, existing graph based applications commonly lack annotated data. GNNs are required to learn latent patterns from a limited amount of training data to perform inferences on a vast amount of test data. The increased complexity of GNNs, as well as a single
Wenqi Wei 0001, Mu Qiao, Divyesh Jadav
openaire   +3 more sources

AdS-GNN -- a Conformally Equivariant Graph Neural Network

open access: yesCoRR
Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine learning. Here we build a neural network that is equivariant under general conformal transformations.
Maksim Zhdanov 0001   +3 more
openaire   +3 more sources

Dual GNNs: Graph Neural Network Learning with Limited Supervision

open access: yesCoRR, 2021
Graph Neural Networks (GNNs) require a relatively large number of labeled nodes and a reliable/uncorrupted graph connectivity structure in order to obtain good performance on the semi-supervised node classification task. The performance of GNNs can degrade significantly as the number of labeled nodes decreases or the graph connectivity structure is ...
Abdullah Alchihabi, Yuhong Guo
openaire   +2 more sources

GNN-EGG: Graph neural network explanations via graph generation

open access: yesNeurocomputing
Graph Neural Networks (GNNs) provide a means for modeling inherently graphical data, such as transportation, social, and molecular networks, but also for enhancing and reducing unstructured data, including text and images. A potential shortcoming is that their predictions are opaque-a black box-hindering broader adoption and refinement.
Art Taychameekiatchai   +6 more
openaire   +4 more sources

DAG-GNN: DAG Structure Learning with Graph Neural Networks

open access: yesCoRR, 2019
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes. A recent breakthrough formulates the problem as a continuous optimization with a structural constraint that ensures acyclicity (Zheng et al ...
Yue Yu 0011   +3 more
openaire   +3 more sources

SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks

open access: yesCoRR
We propose SGS-GNN, a novel supervised graph sparsifier that learns the sampling probability distribution of edges and samples sparse subgraphs of a user-specified size to reduce the computational costs required by GNNs for inference tasks on large graphs.
Siddhartha Shankar Das   +5 more
openaire   +3 more sources

AST-GNN: A Graph Neural Network for Web Tracking Detection

open access: yesProceedings of the 3rd GNNet Workshop on Graph Neural Networking Workshop
Web tracking technology is prevalent on the Internet today, with most websites employing user identification systems that can accurately identify users or devices behind browsers. While numerous works in literature attempt to create machine learning models for detecting these identification systems, many rely on features susceptible to obfuscation ...
Eloi Campeny-Roig   +2 more
openaire   +3 more sources

SA-GNN: Prediction of material properties using graph neural network based on multi-head self-attention optimization

open access: yesAIP Advances
With the development of science and technology and the improvement of hardware computing power, the application of large models in the field of artificial intelligence (AI) has become a current research hotspot Among the focal points in the field of deep
Yasen Cui   +7 more
doaj   +1 more source

Toward Representing Identical Privacy-Preserving Graph Neural Network via Split Learning

open access: yesIEEE Access
In recent years, the fast rise in number of studies on graph neural network (GNN) has put it from the theories research to the real-world application stage.
Yiming Fang, Huiyun Jiao, Risheng Huang
doaj   +1 more source

FL-GNN: Efficient Fusion of Fuzzy Neural Network and Graph Neural Network

open access: yes
Graph Neural Networks (GNNs) have become an important graph feature learning paradigm that is extensively applied to graph inference tasks. However, GNNs still have limitations in some aspects such as representation capability, interpretability, etc.
Boyu Du   +3 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy