Filters








7,985 Hits in 7.2 sec

Attentive Walk-Aggregating Graph Neural Networks [article]

Mehmet F. Demirel, Shengchao Liu, Siddhant Garg, Zhenmei Shi, Yingyu Liang
2022 arXiv   pre-print
We propose a novel GNN model, called AWARE, that aggregates information about the walks in the graph using attention schemes.  ...  In this paper, we aim to design an algorithm incorporating weighting schemes into walk-aggregating GNNs and analyze their effect.  ...  AWARE: Attentive Walk-Aggregating Graph Neural Network We propose AWARE, an end-to-end fully supervised GNN for learning graph embeddings by aggregating information from walks with learned weighting schemes  ... 
arXiv:2110.02667v2 fatcat:ae45s53mbrdybbk7yzfreydpwy

Local Structural Aware Heterogeneous Information Network Embedding Based on Relational Self-Attention Graph Neural Network

Meng Cao, Jinliang Yuan, Ming Xu, Hualei Yu, Chongjun Wang
2021 IEEE Access  
Specifically, we first design a relational self-attention graph neural network model to aggregate heterogeneous information and automatically extract semantic similarity without using meta-paths.  ...  INDEX TERMS Graph neural network, heterogeneous information network, network embedding, social network analysis. VOLUME 9, 2021 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  a two-level attention mechanism for feature aggregation. • HGT [37] : An attention-based graph neural network model for heterogeneous networks, which learns type-specific node embeddings and employs  ... 
doi:10.1109/access.2021.3090055 fatcat:6ynffvfhgvgcndcpd3374jrwyu

Attention-aware heterogeneous graph neural network

Jintao Zhang, Quan Xu
2021 Big Data Mining and Analytics  
In this paper, we propose an Attention-aware Heterogeneous graph Neural Network (AHNN) model to effectively extract useful information from HIN and use it to learn the embedding representation of nodes  ...  As a powerful tool for elucidating the embedding representation of graph-structured data, Graph Neural Networks (GNNs), which are a series of powerful tools built on homogeneous networks, have been widely  ...  [lO] demonstrated 2 Related Work In this paper, we propose an Attention-aware Heterogeneous graph Neural Network (AHNN) for embedding an HIN.  ... 
doi:10.26599/bdma.2021.9020008 fatcat:ceew7ktk7vhy7gxiesgouomiaq

GAHNE: Graph-Aggregated Heterogeneous Network Embedding [article]

Xiaohe Li, Lijie Wen, Chen Qian, Jianmin Wang
2020 arXiv   pre-print
results of downstream tasks based on graph convolutional neural networks.  ...  To address these limitations, we propose a novel Graph-Aggregated Heterogeneous Network Embedding (GAHNE), which is designed to extract the semantics of HINs as comprehensively as possible to improve the  ...  “Heterogeneous graph attention network.”  ... 
arXiv:2012.12517v1 fatcat:7efq3643fffsvdgevrpy7odfhm

GCN for HIN via Implicit Utilization of Attention and Meta-paths [article]

Di Jin, Zhizhi Yu, Dongxiao He, Carl Yang, Philip S. Yu, Jiawei Han
2020 arXiv   pre-print
Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors.  ...  layer-by-layer, realizing the function of attentions for selecting meta-paths in an indirect way.  ...  We further give an effective relaxation and improvement by introducing a new multi-layer propagation which is separated from the aggregation.  ... 
arXiv:2007.02643v1 fatcat:k3jmh4z7lnd3fdshuvx6g4bude

Temporal network embedding using graph attention network

Anuraj Mohan, K V Pramod
2021 Complex & Intelligent Systems  
Adding an attention layer over the GCN can allow the network to provide different importance within various one-hop neighbours.  ...  In this work, we propose a temporal graph attention network (TempGAN), where the aim is to learn representations from continuous-time temporal network by preserving the temporal proximity between nodes  ...  Graph attention network (GAT) [20] is enhancement over GCN which uses an additional attention layer to learn the importance of node neighbourhood during feature aggregation.  ... 
doi:10.1007/s40747-021-00332-x fatcat:jy6q2meccnbqvjhhxkdlmmhnmm

RAW-GNN: RAndom Walk Aggregation based Graph Neural Network [article]

Di Jin, Rui Wang, Meng Ge, Dongxiao He, Xiang Li, Wei Lin, Weixiong Zhang
2022 arXiv   pre-print
Here, we introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method.  ...  The proposed approach integrates the random walk strategy with graph neural networks.  ...  Acknowledgments This research was partly supported by the Natural Science Foundation of China under grants 61876128, the Tianjin Municipal Science and Technology Project (Grant No. 19ZXZNGX00030), and  ... 
arXiv:2206.13953v1 fatcat:5ok76d4zhvb2zhrpft4olunoxi

KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media [article]

Wenqian Zhang, Shangbin Feng, Zilong Chen, Zhenyu Lei, Jundong Li, Minnan Luo
2022 arXiv   pre-print
Finally, we adopt relational graph neural networks for graph-level representation learning and conduct political perspective detection.  ...  Specifically, we firstly generate random walks on external knowledge graphs and infuse them with news text representations.  ...  Finally, KCD learns graph representations with relational graph neural networks and conduct perspective detection with different aggregation strategies.  ... 
arXiv:2204.04046v3 fatcat:spqznksy2fecvo7mmxyar3l63m

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

Liqun Gao, Haiyang Wang, Zhouran Zhang, Hongwu Zhuang, Bin Zhou
2022 Frontiers in Physics  
The majority of studies are based on a homogeneous graph neural network to model the influence between users. However, these studies ignore the impact of events on users in reality.  ...  This study designs an influence prediction model based on a heterogeneous neural network HetInf.  ...  in convolutional neural and attention networks.  ... 
doi:10.3389/fphy.2021.787185 fatcat:smv4l6jd5zdyblh7gfjjgnhwhy

MBHAN: Motif-Based Heterogeneous Graph Attention Network

Qian Hu, Weiping Lin, Minli Tang, Jiatao Jiang
2022 Applied Sciences  
Graph neural networks are graph-based deep learning technologies that have attracted significant attention from researchers because of their powerful performance.  ...  Heterogeneous graph-based graph neural networks focus on the heterogeneity of the nodes and links in a graph.  ...  Motif2vec [25] , for instance, aggregated and shuffled random walk sequences created for both a motif-based higher-order graph and an original graph.  ... 
doi:10.3390/app12125931 fatcat:mexazfmctfgj5n552pu5sglmxi

GraLSP: Graph Neural Networks with Local Structural Patterns [article]

Yilun Jin, Guojie Song, Chuan Shi
2019 arXiv   pre-print
It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node  ...  The walks are then fed into the feature aggregation, where we design various mechanisms to address the impact of structural features, including adaptive receptive radius, attention and amplification.  ...  This work was supported by the National Natural Science Foundation of China (Grant No. 61876006 and No. 61572041).  ... 
arXiv:1911.07675v2 fatcat:222b5aqwjncqdjip6omyw744py

Graphs, Entities, and Step Mixture for Enriching Graph Representation

Kyuyong Shin, Wonyoung Shin, Jung-Woo Ha, Sunyoung Kwon
2021 IEEE Access  
GESM employs a mixture of various steps through random walk to alleviate the oversmoothing problem, an attention mechanism to dynamically reflect interrelations depending on node information, and structure-based  ...  Existing approaches for graph neural networks typically suffer from the oversmoothing issue that results in indistinguishable node representation, as recursive and simultaneous neighborhood aggregation  ...  Conceptual scheme of neighborhood aggregation for three steps (a) in conventional graph neural networks and (b) our method which uses mixture of random walks. FIGURE 4 . 4 FIGURE 4.  ... 
doi:10.1109/access.2021.3121708 fatcat:fb45mshnbvabpjan7mapenrmqa

ATPGNN: Reconstruction of Neighborhood in Graph Neural Networks with Attention-based Topological Patterns

Kehao Wang, Hantao Qian, Xuming Zeng, Mozi Chen, Kezhong Liu, Kai Zheng, Pan Zhou, Dapeng Wu
2021 IEEE Access  
Graph Neural Networks (GNNs) have been applied in many fields of semi-supervised node classification for non-Euclidean data.  ...  Finally, we combine the representation information of remote nodes, graph structure information and feature for each node by attention mechanism, and apply them to learning node representation in graph  ...  Reference [8] proposed a new neural network model-Graph Attention Networks (GAT) based on attention mechanism.  ... 
doi:10.1109/access.2021.3050541 fatcat:pn5uyqnvr5dw3ord6hhytzlgqm

GraLSP: Graph Neural Networks with Local Structural Patterns

Yilun Jin, Guojie Song, Chuan Shi
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node  ...  The walks are then fed into the feature aggregation, where we design various mechanisms to address the impact of structural features, including adaptive receptive radius, attention and amplification.  ...  This work was supported by the National Natural Science Foundation of China (Grant No. 61876006 and No. 61572041).  ... 
doi:10.1609/aaai.v34i04.5861 fatcat:ly4rmrz2cbgu5d4uecryhnhp5y

Graph Representation Learning of Banking Transaction Network with Edge Weight-Enhanced Attention and Textual Information

Naoto Minakawa, Kiyoshi Izumi, Hiroki Sakaji, Hitomi Sano
2022 Companion Proceedings of the Web Conference 2022  
mechanism, using textual information, and designing an efficient combination of existing graph neural networks.  ...  In this paper, we propose a novel approach to capture inter-company relationships from banking transaction data using graph neural networks with a special attention mechanism and textual industry or sector  ...  Graph Isomorphism Network Typical graph neural networks are based on message aggregation from neighbor nodes and update on the aggregated features.  ... 
doi:10.1145/3487553.3524643 fatcat:e6elniezonf7jaozxbdal4gtni
« Previous Showing results 1 — 15 out of 7,985 results