Graph neural network (GNN) is an effective neural architecture for mining graph-structured data, since it can capture the high-order content and topological information on graphs12. It has been widely used in personalization scenarios such as product recommendation13,14,15and content recommendation16t...
GAPointNet: graph attention based point neural network for exploiting local feature of point cloud. Neurocomputing 438, 122–132 (2021). Article Google Scholar Fenton, M. J. et al. Permutationless many-jet event reconstruction with symmetry preserving attention networks. Phys. Rev. D 105, ...
machine-learning vulnerability-detection datacollection graphneuralnetwork Updated Dec 6, 2023 Python zixi-liu / Fraud-Detection-Papers Star 113 Code Issues Pull requests Learning Fraud Detection from research papers and industry applications. machine-learning deep-learning fraud-detection anomaly-detecti...
A library for graph deep learning research deep-learninggraph-generationexplainable-mlself-supervised-learning3d-graphgraph-neural-network UpdatedJul 15, 2024 Python PaddlePaddle/PGL Star1.6k Code Issues Pull requests Discussions Paddle Graph Learning (PGL) is an efficient and flexible graph learning fram...
The recommendation methods based on graph neural network are summarized, focusing on graph neural network and its recent research achievements in the field of recommendation. The recommendation research status and the difficulties in further development are analyzed. According to...
With AG, graph gate neural network is utilized to explore the interactions between features from different grain levels and help learn more discriminative and comprehensive feature representation for each grain level. Based on DG, we employ graph convolutional network to model the category hierarchical ...
(GGNN) have demonstrated ground-breaking performance on many tasks mentioned above. In this survey, we provide a detailed review over existing graph neural network models, systematically categorize the applications, and propose four open problems for future research.大量的学习任务需要处理包含丰富元素间...
Graph Pointer Neural Networks Tianmeng Yang, Yujing Wang, Zhihan Yue, Yaming Yang, Yunhai Tong, Jing Bai AAAI 2022|January 2022 Download BibTex Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and...
In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are ...
The method first constructs a graph using the similarity between samples; secondly the constructed graph is fed into a graph neural network (GNN) for feature mapping, and the samples outputted by the GNN network fuse the feature information of their neighbors, which is beneficial to the ...