Filters








11,007 Hits in 8.6 sec

Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model [article]

Linhao Luo, Yixiang Fang, Xin Cao, Xiaofeng Zhang, Wenjie Zhang
2021 pre-print
To alleviate this issue, in this paper, we propose to exploit the context path to capture the high-order relationship between nodes, and build a Context Path-based Graph Neural Network (CP-GNN) model.  ...  Community detection, aiming to group the graph nodes into clusters with dense inner-connection, is a fundamental graph mining task.  ...  In this paper, we propose a novel model, called the Context Path-based Graph Neural Network (CP-GNN), for detecting communities with nodes of the same target type in the heterogeneous graph.  ... 
doi:10.1145/3459637.3482250 arXiv:2109.02058v1 fatcat:7e67qvtdcnexfodgb4iipokowy

Heterogeneous Graph Matching Networks [article]

Shen Wang, Zhengzhang Chen, Xiao Yu, Ding Li, Jingchao Ni, Lu-An Tang, Jiaping Gui, Zhichun Li, Haifeng Chen, Philip S. Yu
2019 arXiv   pre-print
To address the limitations of existing techniques, we propose MatchGNet, a heterogeneous Graph Matching Network model to learn the graph representation and similarity metric simultaneously based on the  ...  We conduct a systematic evaluation of our model and show that it is accurate in detecting malicious program behavior and can help detect malware attacks with less false positives.  ...  Thus, in this paper, we propose a Graph Neural Network based approach to learn the semantic-level context of program instances.  ... 
arXiv:1910.08074v1 fatcat:hgqew4qbwzfvppiy53vsgeynyu

GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs [article]

Linhao Luo, Yixiang Fang, Moli Lu, Xin Cao, Xiaofeng Zhang, Wenjie Zhang
2022 arXiv   pre-print
We then propose a context path-based graph neural network (CP-GNN) to automatically leverage the semantics in heterogeneous graphs.  ...  , recommendation, and community detection.  ...  CONCLUSION In this paper, we propose a context path-based graph neural network model for relevance measure in heterogeneous graphs, called GSim.  ... 
arXiv:2208.06144v1 fatcat:whp7xd6w2rgfvhpoe4n53prdju

Knowledge Graphs

Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia D'amato, Gerard De Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, Axel-Cyrille Ngonga Ngomo, Axel Polleres (+6 others)
2021 ACM Computing Surveys  
After some opening remarks, we motivate and contrast various graph-based data models, as well as languages used to query and validate knowledge graphs.  ...  In this article, we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse  ...  ACKNOWLEDGMENTS We thank the organisers and attendees of the Dagstuhl Seminar on "Knowledge Graphs" and those who provided feedback on this article.  ... 
doi:10.1145/3447772 fatcat:whwtefhsfjf4djcok7c5jrgtaa

Heterogeneous Graph Matching Networks for Unknown Malware Detection

Shen Wang, Zhengzhang Chen, Xiao Yu, Ding Li, Jingchao Ni, Lu-An Tang, Jiaping Gui, Zhichun Li, Haifeng Chen, Philip S. Yu
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
To address the limitations of existing techniques, we propose MatchGNet, a heterogeneous Graph Matching Network model to learn the graph representation and similarity metric simultaneously based on the  ...  We conduct a systematic evaluation of our model and show that it is accurate in detecting malicious program behavior and can help detect malware attacks with less false positives.  ...  Thus, in this paper, we propose a Graph Neural Network based approach to learn the semantic-level context of program instances.  ... 
doi:10.24963/ijcai.2019/522 dblp:conf/ijcai/WangCYLNTGLCY19 fatcat:rbaxxxslnnajzna2rq4ctrxvmm

Attentional Heterogeneous Graph Neural Network: Application to Program Reidentification [article]

Shen Wang, Zhengzhang Chen, Ding Li, Lu-An Tang, Jingchao Ni, Zhichun Li, Junghwan Rhee, Haifeng Chen, Philip S. Yu
2019 arXiv   pre-print
In this paper, we propose an attentional heterogeneous graph neural network model (DeepHGNN) to verify the program's identity based on its system behaviors.  ...  We formulate the program reidentification as a graph classification problem and develop an effective attentional heterogeneous graph embedding algorithm to solve it.  ...  Attentional Heterogeneous Graph Neural Networks After the graph modeling, a heterogeneous program behavior graph is constructed.  ... 
arXiv:1812.04064v2 fatcat:7vujchgqbfgenjskt66njvgsye

Heterogeneous Hypergraph Embedding for Graph Classification [article]

Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Jiuxin Cao, Yingxia Shao, Nguyen Quoc Viet Hung
2021 arXiv   pre-print
In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise  ...  Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning.  ...  different meta-paths and hyperedge types respectively. • We propose a novel heterogeneous hypergraph neural network to perform representation learning on heterogeneous hypergraphs.  ... 
arXiv:2010.10728v3 fatcat:wrfvahvqsbgwnmeovxe4u5qtai

Heterogeneous Hypergraph Embedding for Graph Classification

Xiangguo Sun, Hongzhi Yin, Bo Liu, Hongxu Chen, Jiuxin Cao, Yingxia Shao, Nguyen Quoc Viet Hung
2021 Proceedings of the 14th ACM International Conference on Web Search and Data Mining  
In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise  ...  Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning.  ...  different meta-paths and hyperedge types respectively. • We propose a novel heterogeneous hypergraph neural network to perform representation learning on heterogeneous hypergraphs.  ... 
doi:10.1145/3437963.3441835 fatcat:mxqbdztybnhghmtqykv6zgpav4

Survey on graph embeddings and their applications to machine learning problems on graphs

Ilya Makarov, Dmitrii Kiselev, Nikita Nikitinsky, Lovro Subelj
2021 PeerJ Computer Science  
As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to  ...  Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding.  ...  Deep learning-based models learn a function mapping a graph in the numeric form to a low-dimensional embedding by optimizing over a broad class of expressive neural network functions.  ... 
doi:10.7717/peerj-cs.357 pmid:33817007 pmcid:PMC7959646 fatcat:ntronyrbgfbedez5dks6h4hoq4

Graph Neural Networks Designed for Different Graph Types: A Survey [article]

Josephine M. Thomas and Alice Moallemy-Oureh and Silvia Beddar-Wiesing and Clara Holzhüter
2022 arXiv   pre-print
Based on this, the young research field of Graph Neural Networks (GNNs) has emerged.  ...  Moreover in the dynamic case, we separate the models in discrete-time and continuous-time dynamic graphs based on their architecture.  ...  The model is designed for detecting fake news in heterogeneous graphs and classifies unlabeled nodes in a given partially labeled graph utilizing a Hierarchical Graph Attention Neural Network.  ... 
arXiv:2204.03080v2 fatcat:52o4dx5ulve3na7vndmbpqhpcm

A Heterogeneous Graph Learning Model for Cyber-Attack Detection [article]

Mingqi Lv, Chengyu Dong, Tieming Chen, Tiantian Zhu, Qijie Song, Yuan Fan
2021 arXiv   pre-print
To effective and efficient detect cyber-attacks from a huge number of system events in the provenance data, we firstly model the provenance data by a heterogeneous graph to capture the rich context information  ...  Then, we perform online cyber-attack detection by sampling a small and compact local graph from the heterogeneous graph, and classifying the key system entities as malicious or benign.  ...  In Pro- A comprehensive survey on graph neural networks.  ... 
arXiv:2112.08986v1 fatcat:rmmiesk3arcktnc2bptqci36gi

Graph Neural Networks for Graph Drawing [article]

Matteo Tiezzi, Gabriele Ciravegna, Marco Gori
2022 arXiv   pre-print
GND are Graph Neural Networks (GNNs) whose learning process can be driven by any provided loss function, such as the ones commonly employed in Graph Drawing.  ...  In this paper, we propose a novel framework for the development of Graph Neural Drawers (GND), machines that rely on neural computation for constructing efficient and complex maps.  ...  ACKNOWLEDGMENT The authors would like to thank Giuseppe Di Battista for the insightful discussions and for useful suggestions on the Graph Drawing literature and methods.  ... 
arXiv:2109.10061v2 fatcat:lu4he24ppbd3lj2wtrz46tdbma

Reinforcement learning on graphs: A survey [article]

Nie Mingshuo, Chen Dongming, Wang Dongqi
2022 arXiv   pre-print
Graph mining tasks arise from many different application domains, ranging from social networks, transportation to E-commerce, etc., which have been receiving great attention from the theoretical and algorithmic  ...  However, these graph mining methods and RL models are dispersed in different research areas, which makes it hard to compare them.  ...  [138] solve the dependence on the handcrafted meta-paths via proposing a RL enhanced heterogeneous GNN model to design different meta-paths for nodes in heterogeneous information networks, and replacing  ... 
arXiv:2204.06127v2 fatcat:7wf6qxnxzza7xbiwjgjmrsrdjq

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks [article]

Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria
2021 arXiv   pre-print
This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context.  ...  We, however, present a graph attention network-based method for DRE where a graph, that contains meaningfully connected speaker, entity, entity-type, and utterance nodes, is constructed.  ...  The prior work proves that heterogeneous graph neural network is a powerful tool in NLP.  ... 
arXiv:2009.05092v3 fatcat:yvl66ojjuzex3py75kbcag5nie

Jointly embedding the local and global relations of heterogeneous graph for rumor detection [article]

Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu
2019 arXiv   pre-print
Then, we model the global relationships among all source tweets, retweets, and users as a heterogeneous graph to capture the rich structural information for rumor detection.  ...  In this paper, we present a novel global-local attention network (GLAN) for rumor detection, which jointly encodes the local semantic and global structural information.  ...  [10] proposed a recurrent neural networks (RNN) based model to learn the text representations of relevant posts over time.  ... 
arXiv:1909.04465v2 fatcat:meju6xiptbeehaiu7qf6emdspa
« Previous Showing results 1 — 15 out of 11,007 results