68 Hits in 4.8 sec

Transferring Knowledge Distillation for Multilingual Social Event Detection [article]

Jiaqian Ren and Hao Peng and Lei Jiang and Jia Wu and Yongxin Tong and Lihong Wang and Xu Bai and Bo Wang and Qiang Yang
2021 arXiv   pre-print
Recently published graph neural networks (GNNs) show promising performance at social event detection tasks.  ...  Thus, we present a GNN that incorporates cross-lingual word embeddings for detecting events in multilingual data streams. The first exploit is to make the GNN work with multilingual data.  ...  detection of events in Twitter data from a knowledge-preserving perspective.  ... 
arXiv:2108.03084v2 fatcat:kiq6t3w7qnfxxa4bvitt6gdpse

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  ...  FinEvent [139] for social network modeling tasks allows transferring cross-lingual social event detection through modeling social messages into heterogeneous graphs.  ...  [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

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [article]

Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, Suhang Wang
2022 arXiv   pre-print
GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias.  ...  Consequently, trustworthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users' trust in GNNs.  ...  Many real-world graphs such as social networks, knowledge graph, and biological networks are heterogeneous graphs, i.e., networks containing diverse types of nodes and/or relationships.  ... 
arXiv:2204.08570v1 fatcat:7c3pkxitrbhgxj6fytn6f3r644

Forgetting Prevention for Cross-regional Fraud Detection with Heterogeneous Trade Graph [article]

Yujie Li, Yuxuan Yang, Xin Yang, Qiang Gao, Fan Zhou
2022 arXiv   pre-print
To this end, this study proposes a novel solution based on heterogeneous trade graphs, namely HTG-CFD, to prevent knowledge forgetting of cross-regional fraud detection.  ...  However, most existing GNNs-based solutions concentrate on either homogeneous graphs or decomposing heterogeneous interactions into several homogeneous connections for convenience.  ...  ACKNOWLEDGMENTS This work was supported by National Natural Science Foundation of China (Grant No. 62102326), the Humanity and Social Science Youth Foundation of Ministry of Education of China (Grant No  ... 
arXiv:2204.10085v2 fatcat:xchx3tvqazc2liityr7r7ufawm

Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks [article]

Yu Zhao, Huaming Du, Ying Liu, Shaopeng Wei, Xingyan Chen, Fuzhen Zhuang, Qing Li, Ji Liu, Gang Kou
2022 arXiv   pre-print
To address this issue, we first construct a more comprehensive Market Knowledge Graph (MKG) which contains bi-typed entities including listed companies and their associated executives, and hybrid-relations  ...  To the best of our knowledge, this study is the first attempt to explore such bi-typed hybrid-relational knowledge graph of stock via heterogeneous GNNs for its spillover effects. • We then propose DANSMP  ...  constructed market graph of stock for its spillover effects. (3) To the best of our knowledge, this work is the first attempt to study stock movement prediction via heterogeneous GNNs.  ... 
arXiv:2201.04965v2 fatcat:3svfwio4xfalveayttzom3idni

Federated Data: Toward New Generation of Credible and Trustable Artificial Intelligence

Fei-Yue Wang, Weishan Zhang, Yonglin Tian, Rui Qin, Xiao Wang, Bin Hu
2021 IEEE Transactions on Computational Social Systems  
"An Ensemble of Heterogeneous Incremental Classifiers for Assisted Reproductive Technology Outcome Prediction" by K. Ranjini, A. Suruliandi, and S. P.  ...  introduces a novel knowledge automation framework for multisource heterogeneous social signals, and the corresponding workflow, models, and application scenarios are also reviewed and concluded.  ... 
doi:10.1109/tcss.2021.3077033 fatcat:ojozfayjjjgkzn3a7xikrgfhqy

2021 Index IEEE Transactions on Computational Social Systems Vol. 8

2021 IEEE Transactions on Computational Social Systems  
Yu, X., +, TCSS Oct. 2021 1143-1152 Computational complexity A Bisubmodular Approach to Event Detection and Prediction in Multivariate Social Graphs.  ...  Wang, R., +, TCSS Aug. 2021 938-945 An Ensemble of Heterogeneous Incremental Classifiers for Assisted Repro-ductive Technology Outcome Prediction.  ...  G Game theory An Upstream-Reciprocity-Based Strategy for Academic Social Networks Using Public Goods Game. Deonauth, N.Y., +, TCSS  ... 
doi:10.1109/tcss.2021.3137918 fatcat:kdc6nwrfbncixnxc5xkjwqvuqq

xFraud: Explainable Fraud Transaction Detection on Heterogeneous Graphs [article]

Susie Xi Rao, Shuai Zhang, Zhichao Han, Zitao Zhang, Wei Min, Zhiyao Chen, Yinan Shan, Yang Zhao, Ce Zhang
2020 arXiv   pre-print
representations for malicious transaction detection from the heterogeneous transaction graph via a self-attentive heterogeneous graph neural network, and an explainer that generates meaningful and human  ...  At online retail platforms, it is crucial to actively detect risks of fraudulent transactions to improve our customer experience, minimize loss, and prevent unauthorized chargebacks.  ...  Fraud detection has been an emerging topic for e-commerce and social media companies.  ... 
arXiv:2011.12193v1 fatcat:kkpaheaqpfgdfhmvusqngglobq

Implicit sentiment analysis based on graph attention neural network

Shanliang Yang, Linlin Xing, Yongming Li, Zheng Chang
2021 Engineering Reports  
In order to solve the problem of multiple attention preserving repeated information, orthogonal attention constraint was used to make different attention store different emotional information; given the  ...  Network), HetGNN (Heterogeneous GNN), Heterogeneity Attention Network (HAN).  ...  events in society.  ... 
doi:10.1002/eng2.12452 fatcat:27bmtg5v4fdsfda22dcmvcrx7i

Graph Neural Networks for Natural Language Processing: A Survey [article]

Lingfei Wu, Yu Chen, Kai Shen, Xiaojie Guo, Hanning Gao, Shucheng Li, Jian Pei, Bo Long
2021 arXiv   pre-print
To the best of our knowledge, this is the first comprehensive overview of Graph NeuralNetworks for Natural Language Processing.  ...  We propose a new taxonomy of GNNs for NLP, whichsystematically organizes existing research of GNNs for NLP along three axes: graph construction,graph representation learning, and graph based encoder-decoder  ...  Event detection with multi-order graph convolu- tion and aggregated attention.  ... 
arXiv:2106.06090v1 fatcat:zvkhinpcvzbmje4kjpwjs355qu

Graph similarity learning for change-point detection in dynamic networks [article]

Deborah Sulem, Henry Kenlay, Mihai Cucuringu, Xiaowen Dong
2022 arXiv   pre-print
Importantly, our method does not require prior knowledge on the network generative distribution and is agnostic to the type of change-points; moreover, it can be applied to a large variety of networks,  ...  This task is often termed network change-point detection and has numerous applications, such as fraud detection or physical motion monitoring.  ...  To our knowledge, only one prior work has incorporated GNN layers in a method for changepoint detection, but has done so in the context of multivariate time series [47] .  ... 
arXiv:2203.15470v1 fatcat:dax7fxusazetva2a6wb4z35hky

A Comprehensive Survey on Graph Anomaly Detection with Deep Learning [article]

Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z. Sheng, Hui Xiong, Leman Akoglu
2021 arXiv   pre-print
, and social spam.  ...  ., data records or events) that deviate significantly from others.  ...  Specifically, they modeled social platforms as heterogeneous social graphs such that the affluent relationships between users, tweets, hashtags and links were effectively captured.  ... 
arXiv:2106.07178v4 fatcat:efargsqnxndqbfqat2q5iz54u4

A Comprehensive Survey on Graph Neural Networks [article]

Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu
2019 arXiv   pre-print
In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields.  ...  [168] , electrical health records modeling [169] , [170] , brain networks [171] , event detection [172] , and combinatorial optimization [173] .  ...  Heterogenity The majority of current GNNs assume homogeneous graphs.  ... 
arXiv:1901.00596v4 fatcat:xxuchvawonhczay2sgjgzw5wgu

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
Image adapted from [11] . to internal or external events.  ...  Graph neural networks (GNNs) are a deep learning-based method that operate over graphs, and have been adopted in diverse fields including social network analysis and drug discovery using computational  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Personalized News Recommendation: Methods and Challenges

Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Xing Xie
2022 ACM Transactions on Information Systems  
+Category+Event Type Graph LSTM+Attention+Node2Vector IGNN [161] 2019 Title+Entity+User-News Graph KCNN+GNN INNR [167] 2019 Heterogeneous Graph Node2vec GNewsRec [70] 2020 Title+Entity+Heterogeneous  ...  In addition, user behaviors such as comments and sharing on social media may also provide rich clues for detecting news that contain misinformation and harmful content [4, 177] .  ... 
doi:10.1145/3530257 fatcat:xzghh6cut5ahhgxz4mkzgy74ja
« Previous Showing results 1 — 15 out of 68 results