Filters








23,830 Hits in 5.2 sec

The knowledge graph as the default data model for learning on heterogeneous knowledge

Xander Wilcke, Peter Bloem, Victor de Boer, Michel Dumontier
2017 Data Science  
. / The knowledge graph as the default data model for learning on heterogeneous knowledge from their data, often creating a derivative of the original data in the process, they now prefer to feed their  ...  graph as the default data model for this kind of knowledge and b) develop end-to-end models that can directly consume these knowledge graphs.  ...  . / The knowledge graph as the default data model for learning on heterogeneous knowledge Acknowledgements.  ... 
doi:10.3233/ds-170007 dblp:journals/datasci/WilckeBB17 fatcat:o5hclal77zayheldkar3lb3hf4

Bond Default Prediction Based on Deep Learning and Knowledge Graph Technology

Ma Chi, Sun Hongyan, Wang Shaofan, Lu Shengliang, Li Jingyan
2021 IEEE Access  
Therefore, this paper uses multisource information from bonds and issuers as well as macroeconomic data to predict bond defaults based on a knowledge graph and deep learning technology.  ...  On the basis of constructing a bond knowledge graph, knowledge representation learning technology is used to vectorize the knowledge in the graph, and the extracted vectors are inputted into the deep learning  ...  steps. • Construct a bond knowledge graph based on existing data. • For the constructed knowledge map, the knowledge representation learning model is used to learn, and the entity matrix and the relation  ... 
doi:10.1109/access.2021.3052054 fatcat:yvpprjocyrg5tkuf37bikiighu

Heterogeneous Information Network based Default Analysis on Banking Micro and Small Enterprise Users [article]

Zheng Zhang, Yingsheng Ji, Jiachen Shen, Xi Zhang, Guangwen Yang
2022 arXiv   pre-print
In this paper, we consider a graph of banking data, and propose a novel HIDAM model for the purpose.  ...  Specifically, we attempt to incorporate heterogeneous information network with rich attributes on multi-typed nodes and links for modeling the scenario of business banking service.  ...  To our knowledge, this is the first work of graph-based heterogeneous data mining for credit risk analysis in commercial banks.  ... 
arXiv:2204.11849v2 fatcat:jljivqnsrvdczi26valy5o6luy

edge2vec: Representation learning using edge semantics for biomedical knowledge discovery [article]

Zheng Gao, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner, Brian Foote, David Wild, Qi Yu, Ying Ding
2019 arXiv   pre-print
Representation learning provides new and powerful graph analytical approaches and tools for the highly valued data science challenge of mining knowledge graphs.  ...  Results show that by considering edge-types into node embedding learning in heterogeneous graphs, edge2vec significantly outperforms state-of-the-art models on all three tasks.  ...  Accordingly Wilcke et al. published: "The knowledge graph as the default data model for learning on heterogeneous knowledge." [3] .  ... 
arXiv:1809.02269v3 fatcat:5m67e7nc4jfkfag7qdynzerouq

KGSecConfig: A Knowledge Graph Based Approach for Secured Container Orchestrator Configuration [article]

Mubin Ul Haque, M. Mehdi Kholoosi, M. Ali Babar
2021 arXiv   pre-print
We also demonstrate the utilization of the knowledge graph for automated misconfiguration mitigation in a Kubernetes cluster.  ...  Our solution leverages keyword and learning models to systematically capture, link, and correlate heterogeneous and multi-vendor configuration space in a unified structure for supporting automation of  ...  learning model for minimizing the effect of bias.  ... 
arXiv:2112.12595v1 fatcat:3ddw5irclrgxfooe3chpwzqfpi

A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information [article]

Chaoyang Wang, Zhiqiang Guo, Guohui Li, Jianjun Li, Peng Pan, Ke Liu
2021 arXiv   pre-print
Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively  ...  network) collaborative filtering method based on heterogeneous graphs.  ...  As these graphs naturally contain at least two different types of nodes, i.e., user u and item v, they belong to the heterogeneous graphs (heterographs for short).  ... 
arXiv:2010.07027v4 fatcat:syx5nj626banlo6f7bk2tye7r4

edge2vec: Representation learning using edge semantics for biomedical knowledge discovery

Zheng Gao, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner, Brian Foote, David Wild, Ying Ding, Qi Yu
2019 BMC Bioinformatics  
Representation learning provides new and powerful graph analytical approaches and tools for the highly valued data science challenge of mining knowledge graphs.  ...  Results show that by considering edge-types into node embedding learning in heterogeneous graphs, edge2vec significantly outperforms state-of-the-art models on all three tasks.  ...  Accordingly Wilcke et al. published: "The knowledge graph as the default data model for learning on heterogeneous knowledge" [1] .  ... 
doi:10.1186/s12859-019-2914-2 fatcat:6oiu3qoi7ncbppiaetzwqx6zxm

Reinforcement Learning over Knowledge Graphs for Explainable Dialogue Intent Mining

Kai Yang, Xinyu Kong, Yafang Wang, Jie Zhang, Gerard De Melo
2020 IEEE Access  
Finally, we consider a wide range of recently proposed knowledge graph-based recommender systems as baselines, mostly based on deep reinforcement learning and our method performs best.  ...  We rely on policy-guided reinforcement learning to identify paths in a graph to confirm concrete paths of inference that serve as interpretable explanations.  ...  The main contributions of this paper are as follows: 1) We use multi-turn dialogue data to construct a knowledge graph and train a node embedding model for this knowledge graph, which mainly includes the  ... 
doi:10.1109/access.2020.2991257 fatcat:wtgscficrzdozp25zy2arysxpi

HI2Rec: Exploring Knowledge in Heterogeneous Information for Movie Recommendation

Ming He, Bo Wang, Xiangkun Du
2019 IEEE Access  
We extract the movie-related information from the Linked Open Data and then leverage the knowledge representation learning approach to embed this information as well as real-world datasets' information  ...  Recently, knowledge graphs have been proven to be highly effective to recommender systems, because they are able to fuse various recommendation models and can handle the issues of data sparsity and cold  ...  knowledge graph) to model heterogeneous information.  ... 
doi:10.1109/access.2019.2902398 fatcat:67a5wfv3fvbuhb2ybfrhbkrlgi

Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation [article]

Yankai Chen, Menglin Yang, Yingxue Zhang, Mengchen Zhao, Ziqiao Meng, Jianye Hao, Irwin King
2022 arXiv   pre-print
LKGR facilitates better modeling of scale-free tripartite graphs after the data unification.  ...  Via unifying the KG with user-item interactions into a tripartite graph, recent works explore the graph topologies to learn the low-dimensional representations of users and items with rich semantics.  ...  How to simultaneously learn the graph structure and temporal information in a unified framework is a good direction to work on. (2) Hyperbolic modeling mainly aims to learn the real scale-free data with  ... 
arXiv:2108.06468v3 fatcat:crvllwrugvhsvc7h2lg3skchdu

Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph [article]

Nuttapong Chairatanakul, Noppayut Sriwatanasakdi, Nontawat Charoenphakdee, Xin Liu, Tsuyoshi Murata
2021 arXiv   pre-print
First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibility to use graph neural networks for cross-lingual transfer.  ...  Its robustness allows the usage of a wider range of dictionaries such as an automatically constructed dictionary and crowdsourced dictionary, which are convenient for real-world applications.  ...  The performance of all methods also depends on the data provided for them. To the best of our knowledge, there does not exist any methods that use the same input source as our proposed DHGNets.  ... 
arXiv:2109.04400v2 fatcat:vtugtbf2ubh6jdavktnqbjyoey

A Review on Graph Neural Network Methods in Financial Applications

Jianian Wang, Sheng Zhang, Yanghua Xiao, Rui Song
2022 Journal of Data Science  
Due to the complexity and volatility of the financial market, the graph constructed on the financial data is often heterogeneous or time-varying, which imposes challenges on modeling technology.  ...  With multiple components and relations, financial data are often presented as graph data, since it could represent both the individual features and the complicated relations.  ...  Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR). Kudo W, Nishiguchi M, Toriumi F (2020).  ... 
doi:10.6339/22-jds1047 fatcat:lpkkobcferal3p7l5wanydm7ay

Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning

Zhuoren Jiang, Jian Wang, Lujun Zhao, Changlong Sun, Yao Lu, Xiaozhong Liu
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
To address these problems, we propose an innovative solution, Traceable Heterogeneous Graph Representation Learning (THGRL).  ...  Unlike prior text-based aspect detection works, THGRL explores latent domain aspect category connections via massive user behavior information on a heterogeneous graph.  ...  Compared with the simple models, the deep learning family needs more training data for optimization. • Different Mining Methods on Textual Information.  ... 
doi:10.1145/3357384.3357989 dblp:conf/cikm/JiangWZSLL19 fatcat:35qh5tblhjfqfpm3lxfv3ile24

Usage of the machine learning to organize time series and find anomalies

A.S. Kopyrin, E.V. Vidishcheva, Yu.I. Dreizis, V. Breskich, A. Zheltenkov, Y. Dreizis
2020 E3S Web of Conferences  
The subject of the study is the process of collecting, preparing, and searching for anomalies on data from heterogeneous sources.  ...  The technology proposed by the authors involves the joint use of methods for building a fuzzy time series and machine lexical matching on a thesaurus network, as well as the use of a universal database  ...  Besides, as more data is generated, collected, and analyzed on an ever-increasing scale, there is an increasing need for methods to purify source information and detect knowledge based on it.  ... 
doi:10.1051/e3sconf/202022401017 fatcat:qzeonrrlcvehronrn62ysr25tq

PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python [article]

Haiping Lu, Xianyuan Liu, Robert Turner, Peizhen Bai, Raivo E Koot, Shuo Zhou, Mustafa Chasmai, Lawrence Schobs
2021 arXiv   pre-print
We present Pykale - a Python library for knowledge-aware machine learning on graphs, images, texts, and videos to enable and accelerate interdisciplinary research.  ...  We build PyKale on PyTorch and leverage the rich PyTorch ecosystem.  ...  ACKNOWLEDGMENTS The development of PyKale is partially supported by the Innovator Awards: Digital Technologies from the Wellcome Trust (grant 215799/Z/19/Z).  ... 
arXiv:2106.09756v1 fatcat:mnuxoz26mbdexn5cobnpqhkmyi
« Previous Showing results 1 — 15 out of 23,830 results