Results 51 to 60 of about 6,341,676 (193)
Node-attribute graph layout for small-world networks [PDF]
, 2011 Small-world networks are a very commonly occurring type of graph in the real-world, which exhibit a clustered structure that is not well represented by current graph layout algorithms. In many cases we also have information about the nodes in such graphs,
Joe Faith +3 more
core +1 more source
Graph Tree Networks: a graph representation learning framework
, 2023 Fang, XiaoGraph Neural Networks (GNNs) have been successfully applied in many areas to solve real-world problems. Among various architectures of GNNs, the class of spatial-based convolutional GNNs (Conv-GNNs) has gained particular attention due to its ...
Wu, Nan
core +1 more source
Supervised Attention Using Homophily in Graph Neural Networks [PDF]
, 2023 Graph neural networks have become the standard approach for dealing with learning problems on graphs. Among the different variants of graph neural networks, graph attention networks (GATs) have been applied with great success to different tasks.
Vazirgiannis, Michalis +2 more
core +1 more source
SEA: Graph Shell Attention in Graph Neural Networks
, 2023 A common issue in Graph Neural Networks (GNNs) is known as over-smoothing. By increasing the number of iterations within the message-passing of GNNs, the nodes' representations of the input graph align with each other and become indiscernible. Recently, it has been shown that increasing a model's complexity by integrating an attention mechanism yields ...
Christian M. M. Frey +2 more
openaire +2 more sources
Graph Attention Networks with Positional Embeddings [PDF]
, 2021 Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily -- neighboring nodes having similar features and labels--, and therefore may not be at their full potential when dealing with non-homophilic graphs.
Liheng Ma +2 more
openaire +3 more sources
Adaptive Depth Graph Attention Networks
CoRR, 2023 As one of the most popular GNN architectures, the graph attention networks (GAT) is considered the most advanced learning architecture for graph representation and has been widely used in various graph mining tasks with impressive results. However, since GAT was proposed, none of the existing studies have provided systematic insight into the ...
Jingbo Zhou +3 more
openaire +2 more sources
Graph Attention Networks With Local Structure Awareness for Knowledge Graph Completion
IEEE Access, 2020 Graph neural networks have been proven to be very effective for representation learning of knowledge graphs. Recent methods such as SACN and CompGCN, have achieved the most advanced results in knowledge graph completion.
Kexi Ji, Bei Hui, Guangchun Luo
doaj +1 more source
Graph Convolutional Networks and Attention-Based Outlier Detection
IEEE Access, 2022 Outlier detection is a significant research direction in machine learning and has many applications in finance, network security, and other areas. Outlier detection of Euclidean datasets is a mainstream problem in outlier detection.
Rui Qiu +4 more
doaj +1 more source
Predicting Propositional Satisfiability Based on Graph Attention Networks
International Journal of Computational Intelligence Systems, 2022 Boolean satisfiability problems (SAT) have very rich generic and domain-specific structures. How to capture these structural features in the embedding space and feed them to deep learning models is an important factor influencing the use of neural ...
Wenjing Chang, Hengkai Zhang, Junwei Luo
doaj +1 more source
Dual-Attention Graph Convolutional Network [PDF]
, 2020 Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative features from texts due to the main issue of graph variants incurred by the textual complexity and diversity.
Xueya Zhang +4 more
openaire +3 more sources