228,060 Hits in 7.0 sec

Name Disambiguation Based on Graph Convolutional Network

Ya Chen, Hongliang Yuan, Tingting Liu, Nan Ding, Pengwei Wang
2021 Scientific Programming  
The nodes in the graphs contain attribute features and the edges contain linkage features. The graphs are then fed to a specialized GCN and output a hybrid representation.  ...  We first build paper-to-paper graphs, coauthor graphs, and paper-to-author graphs for each reference item of a name.  ...  Component Contribution Analysis Only use global representation. e global representation learns the attribute information of papers and authors.  ... 
doi:10.1155/2021/5577692 fatcat:ash4rav2uvedbbjcsvod6cyybq

Automatic Authorship Detection Using Textual Patterns Extracted from Integrated Syntactic Graphs

Helena Gómez-Adorno, Grigori Sidorov, David Pinto, Darnes Vilariño, Alexander Gelbukh
2016 Sensors  
This graph-based representation allows integrating different levels of language description into a single structure.  ...  Our results show that our textual patterns are useful for the task of authorship attribution.  ...  Another graph-based text representation model was proposed by [30] using the word semantic space. The authors also proposed a method of computing text similarity.  ... 
doi:10.3390/s16091374 pmid:27589740 pmcid:PMC5038652 fatcat:ieymx7ngzzacbbodluf7bt6poe

A Graph-Based Author Name Disambiguation Method and Analysis via Information Theory

Yingying Ma, Youlong Wu, Chengqiang Lu
2020 Entropy  
In this paper, we propose a novel name disambiguation model based on representation learning which incorporates attributes and relationships.  ...  However, methods of feature extraction using attributes cause inflexibility of models while solutions based on relationship graph network ignore the information contained in the features.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/e22040416 pmid:33286190 fatcat:v7mk4o6mrbf2li4ma4mpunxkky

Text Analysis Using Different Graph-Based Representations

Esteban Castillo Juarez, Ofelia Cervantes Villagómez, Darnes Vilariño Ayala
2018 Journal of Computacion y Sistemas  
This paper presents an overview of different graph-based representations proposed to solve text classification tasks.  ...  For each text classification task the type of graph created as well as the benefits of using it are presented and discussed.  ...  The authors would also like to thank Daniel Macías Galindo and David Báez López for their invaluable help reviewing this manuscript.  ... 
doi:10.13053/cys-21-4-2551 fatcat:oheaazjd4fabdayuehpfvpg65e

Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks [article]

Qingyun Sun, Hao Peng, Jianxin Li, Senzhang Wang, Xiangyu Dong, Liangxuan Zhao, Philip S. Yu, Lifang He
2021 arXiv   pre-print
Furthermore, a semantic-level attention mechanism is adopted to fuse multiple meta-path based representations.  ...  We divided papers into small blocks based on discriminative author attributes and blocks of the same author will be merged according to pairwise classification results of MA-PairRNN.  ...  • GHOST [2]: GHOST use affinity propagation algorithm for clustering on a co-authors graph where the node distance is measured based on the number of valid paths. • Louppe et al. [3]: This method trains  ... 
arXiv:2008.13099v4 fatcat:kwlfwoh7j5ffll4vgfi4ncmjy4

Understanding Art through Multi-Modal Retrieval in Paintings [article]

Noa Garcia, Benjamin Renoust, Yuta Nakashima
2019 arXiv   pre-print
representations in artistic images.  ...  In computer vision, visual arts are often studied from a purely aesthetics perspective, mostly by analysing the visual appearance of an artistic reproduction to infer its style, its author, or its representative  ...  Figure 3 . 3 ContextNet predicts the painting attributes, such as type, school, timeframe, or author, by fine-tuning a ResNet model based on the information captured by an artistic Knowlegde Graph. between  ... 
arXiv:1904.10615v1 fatcat:7szy5ph7tbb43nxby7ocizgtwe

GPT-GNN: Generative Pre-Training of Graph Neural Networks [article]

Ziniu Hu and Yuxiao Dong and Kuansan Wang and Kai-Wei Chang and Yizhou Sun
2020 arXiv   pre-print
GPT-GNN introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph.  ...  We factorize the likelihood of the graph generation into two components: 1) Attribute Generation and 2) Edge Generation.  ...  After getting the paper and author node representations from GNNs, we use a Neural Tensor Network to get the probability of each author-paper pair to be linked.  ... 
arXiv:2006.15437v1 fatcat:h5jithn2uvginbechslaufc7cy

Quick survey of graph-based fraud detection methods [article]

Paul Irofti, Andrei Patrascu, Andra Baltoiu
2021 arXiv   pre-print
We present a survey on anomaly detection techniques used for fraud detection that exploit both the graph structure underlying the data and the contextual information contained in the attributes.  ...  Most commonly, these networks are represented as attributed graphs, with numerical features complementing relational information.  ...  A latent attributed network representation is learned in [74] by using a number of network walks.  ... 
arXiv:1910.11299v3 fatcat:zyupd4ezxrgw3f7g5utzihy6qi

A Graphical Environment For Petri Nets Ina Tool Based On Meta-Modelling And Graph Grammars

Raida El Mansouri, Elhillali Kerkouche, Allaoua Chaoui
2008 Zenodo  
In this paper, we propose an approach based on the combined use of Meta-modelling and Graph Grammars to automatically generate a visual modelling tool for INA for analysis purposes.  ...  We have also proposed a graph grammar to automatically generate INA description of the graphically specified Petri net models.  ...  In this paper we propose a framework (a tool) based on the combined use of Meta-Modeling and Graph Grammars to generate a graphical environment for INA tool allowing the user to create the graphical representation  ... 
doi:10.5281/zenodo.1074810 fatcat:abo54vwq5rdabotyzjjfofgm5i

The Download Estimation task on KDD Cup 2003

Janez Brank, Jure Leskovec
2003 SIGKDD Explorations  
The task requires us to estimate how many times a paper has been downloaded in the first 60 days after it has been published on, a preprint server for papers on physics and related areas.  ...  The training data consists of approximately 29000 papers, the citation graph, and information about the downloads of a subset of these papers.  ...  Table 1 : 1 The performance of various representations based on the author, abstract, and address features. Table 2 : 2 Summary of experiments with attributes based on the citation graph.  ... 
doi:10.1145/980972.980997 fatcat:emjzgflrxzepvipyv24djal3ym

Learning semantic Image attributes using Image recognition and knowledge graph embeddings [article]

Ashutosh Tiwari, Sandeep Varma
2020 arXiv   pre-print
In this paper, we propose a shared learning approach to learn semantic attributes of images by combining a knowledge graph embedding model with the recognized attributes of images.  ...  Structured semantic representation of the content of an image and knowledge graph embeddings can provide a unique representation of semantic relationships between image entities.  ...  ACKNOWLEDGEMENT The authors would like to extend their gratitude to all whose help and advice led to the completion of this work.  ... 
arXiv:2009.05812v1 fatcat:uquxuxscf5fgpfrjs6xhx6pbge

Vector Representation for Sub-Graph Encoding to Resolve Entities

Jinhong K. Guo, David Van Brackle, Nicolas Lofaso, Martin O. Hofmann
2016 Procedia Computer Science  
Our approach is insensitive to small variations in relational graph representation.  ...  Traditional graph comparison techniques rely on finding precise matches of a significant part of the graph structure, and require custom comparison functions for every type of attribute and every type  ...  Most of the performance evaluations published use only a static dataset, such as resolving authors based on a bibliography database, where all the information associated with each node (author) is available  ... 
doi:10.1016/j.procs.2016.09.342 fatcat:mkapoxzbi5gi3frlso63vitdlu

Application of Clustering to Analyze Academic Social Networks

Sobha Rani K, Raju KVSVN, V.Valli Kumari
2013 International journal of Web & Semantic Technology  
When a social network is represented as a graph with members as nodes and their relation as edges, graph mining would be suitable for statistical analysis.  ...  Social network is a group of individuals with diverse social interactions amongst them.  ...  GRAPH REPRESENTATION OF SOCIAL NETWORKS As stated by Han [18] , information of a social network is heterogeneous and the multi-relational data can be represented as a graph or network.  ... 
doi:10.5121/ijwest.2013.4202 fatcat:cv7ifutow5egjex3kf4j3kl5uq

Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval

Sebastian Schuster, Ranjay Krishna, Angel Chang, Li Fei-Fei, Christopher D. Manning
2015 Proceedings of the Fourth Workshop on Vision and Language  
Recent work in computer vision has shown that a graph-based semantic representation called a scene graph is an effective representation for very detailed image descriptions and for complex queries for  ...  We present a rule-based and a classifierbased scene graph parser whose output can be used for image retrieval.  ...  The second author is also supported by a Magic Grant from The Brown Institute for Media Innovation.  ... 
doi:10.18653/v1/w15-2812 dblp:conf/acl-vl/SchusterKCFM15 fatcat:g3p3uwripjcbjcbfloflwdtniu

A Representation Model of Trust Relationships with Delegation Extensions [chapter]

Isaac Agudo, Javier Lopez, Jose A. Montenegro
2005 Lecture Notes in Computer Science  
In this paper, and after overviewing previous works using logic languages, we present a proposal for graph representation of authorization and delegation statements.  ...  Our proposal is based on Varadharajan et al. solution, though improve several elements of that work. We also discuss about the possible implementation of our proposal using attribute certificates.  ...  Acknowledgements This paper is an outcome of the work performed in three Research Projects where the different co-authors have been involved.  ... 
doi:10.1007/11429760_9 fatcat:l7pybf6kafcjfhsrx7nai34fcy
« Previous Showing results 1 — 15 out of 228,060 results