Filters








126,773 Hits in 6.4 sec

What is Event Knowledge Graph: A Survey [article]

Saiping Guan, Xueqi Cheng, Long Bai, Fujun Zhang, Zixuan Li, Yutao Zeng, Xiaolong Jin, Jiafeng Guo
2022 arXiv   pre-print
Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation  ...  This paper provides a comprehensive survey of EKG from history, ontology, instance, and application views.  ...  Thus, it is necessary to go deep into events. In this way, a comprehensive survey on EKG is of great importance.  ... 
arXiv:2112.15280v2 fatcat:szx75hnmbjem3cyltefxybanai

Graph Kernels: A Survey

Giannis Nikolentzos, Giannis Siglidis, Michalis Vazirgiannis
2021 The Journal of Artificial Intelligence Research  
The goal of this survey is to provide a unifying view of the literature on graph kernels. In particular, we present a comprehensive overview of a wide range of graph kernels.  ...  Graph kernels have attracted a lot of attention during the last decade, and have evolved into a rapidly developing branch of learning on structured data.  ...  The answer is that in contrast to the first two above surveys, this survey is much more thorough and covers a larger number of kernels.  ... 
doi:10.1613/jair.1.13225 fatcat:o7whugpf3rd7hf7g7e7gcxhoyi

Graph Kernels: A Survey [article]

Giannis Nikolentzos and Giannis Siglidis and Michalis Vazirgiannis
2019 arXiv   pre-print
The goal of this survey is to provide a unifying view of the literature on graph kernels. In particular, we present a comprehensive overview of a wide range of graph kernels.  ...  Graph kernels have attracted a lot of attention during the last decade, and have evolved into a rapidly developing branch of learning on structured data.  ...  The answer is that in contrast to the existing survey, this survey is much more thorough and covers a larger number of kernels.  ... 
arXiv:1904.12218v1 fatcat:shfa4lw4eja2rayvubrph6me3m

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
In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties.  ...  Nevertheless, an overview on which graph types can be modeled by GNNs is missing.  ...  Acknowledgment The GAIN-project is funded by the Ministry of Education and Research Germany (BMBF), under the funding code 01IS20047A, according to the 'Policy for the funding of female junior researchers  ... 
arXiv:2204.03080v2 fatcat:52o4dx5ulve3na7vndmbpqhpcm

Representation Learning for Dynamic Graphs: A Survey [article]

Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, Pascal Poupart
2020 arXiv   pre-print
In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs.  ...  Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs.  ...  We survey techniques that deal with discreteand/or continuous-time events. The survey is structured as follows.  ... 
arXiv:1905.11485v2 fatcat:zdzxidx3mjeghpminvbllgc2we

A Survey of Graph Pebbling [article]

Glenn Hurlbert
2004 arXiv   pre-print
We survey results on the pebbling numbers of graphs as well as their historical connection with a number-theoretic question of Erd\H os and Lemke.  ...  Finally, we relate the question of the existence of pebbling thresholds to a strengthening of the normal property of posets, and show that the multiset lattice is not supernormal.  ...  In this paper we survey the current knowledge regarding the many questions surrounding this simple pebbling operation.  ... 
arXiv:math/0406024v1 fatcat:bponxlwumngilc7fcs6j3z2tc4

Scene Graph Generation: A Comprehensive Survey [article]

Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Mingtao Feng, Xia Zhao, Qiguang Miao, Syed Afaq Ali Shah, Mohammed Bennamoun
2022 arXiv   pre-print
Although this is a challenging task, the community has proposed a lot of SGG approaches and achieved good results.  ...  This survey will help readers to develop a better understanding of the current research status and ideas.  ...  Statistical Priors: The simplest way to use prior knowledge is to think that an event should happen this time since it almost always does. This is called statistical prior. Baier et al.  ... 
arXiv:2201.00443v2 fatcat:s4w7sdf6dndzneujly54srh5c4

A Survey on Graph Kernels [article]

Nils M. Kriege, Fredrik D. Johansson, Christopher Morris
2019 arXiv   pre-print
This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years.  ...  We compare the performance of popular kernels with several baseline methods and study the effect of applying a Gaussian RBF kernel to the metric induced by a graph kernel.  ...  has been supported by the German Research Foundation (DFG) within the Collaborative Research Center SFB 876 "Providing Information by Resource-Constrained Data Analysis", project A6 "Resource-efficient Graph  ... 
arXiv:1903.11835v1 fatcat:3rgyn7kbp5h57j5552f2lcdkai

A survey on graph kernels

Nils M. Kriege, Fredrik D. Johansson, Christopher Morris
2020 Applied Network Science  
This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years.  ...  We compare the performance of popular kernels with several baseline methods and study the effect of applying a Gaussian RBF kernel to the metric induced by a graph kernel.  ...  Acknowledgements We thank Pinar Yanardag, Lu Bai, Giannis Nikolentzos, Marion Neumann, and Franceso Orsini for providing their graph kernel source code.  ... 
doi:10.1007/s41109-019-0195-3 fatcat:xblybuqyf5ezbey7ae6udfexse

A Survey on Graph Representation Learning Methods [article]

Shima Khoshraftar, Aijun An
2022 arXiv   pre-print
Graphs representation learning has been a very active research area in recent years.  ...  The goal of graph representation learning is to generate graph representation vectors that capture the structure and features of large graphs accurately.  ...  To the best of our knowledge, there are several other surveys and books on graph representation learning.  ... 
arXiv:2204.01855v2 fatcat:e5p76ipn6jgkzkajvucrvsa55e

Graph-based Anomaly Detection and Description: A Survey [article]

Leman Akoglu and Hanghang Tong and Danai Koutra
2014 arXiv   pre-print
This survey aims to provide a general, comprehensive, and structured overview of the state-of-the-art methods for anomaly detection in data represented as graphs.  ...  We conclude our survey with a discussion on open theoretical and practical challenges in the field.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ... 
arXiv:1404.4679v2 fatcat:y6nsswymcfc2pa7qe7zrjzc7wq

A Survey on Distributed Graph Pattern Matching in Massive Graphs

Sarra Bouhenni, Saïd Yahiaoui, Nadia Nouali-Taboudjemat, Hamamache Kheddouci
2021 ACM Computing Surveys  
of big graphs processing, e.g., Think-Like-A-Vertex and its derivatives.  ...  However, massive graphs generated by mostly social networks require a distributed storing and processing of the data over multiple machines, thus, requiring GPM to be revised by adopting new paradigms  ...  Acknowledgments This work is supported by the Franco-Algerian collaborative program PHC Tassili BiGreen N • 18 MDU 111 and by the DGRSDT grant FNRSDT N • 253.  ... 
doi:10.1145/3439724 fatcat:vib22wz2zffo3c5alriufetwaa

Threat Detection and Investigation with System-level Provenance Graphs: A Survey [article]

Zhenyuan Li, Qi Alfred Chen, Runqing Yang, Yan Chen
2020 arXiv   pre-print
A comprehensive provenance graph-based threat detection system can be divided into three modules, namely, "data collection module", "data management module", and "threat detection modules".  ...  In this paper, we firstly introduce the basic concepts about system-level provenance graph and proposed typical system architecture for provenance graph-based threat detection and investigation.  ...  According to the survey results in [25] , for a typical bank with 20,000 hosts, about 70 PB of logs are generated annually. How to find out suspicious events timely is also challenging.  ... 
arXiv:2006.01722v3 fatcat:ofx2geac3rggvo5kz3zenbmpvq

Graph Summarization Methods and Applications: A Survey [article]

Yike Liu, Tara Safavi, Abhilash Dighe, Danai Koutra
2018 arXiv   pre-print
This survey is a structured, comprehensive overview of the state-of-the-art methods for summarizing graph data. We first broach the motivation behind, and the challenges of, graph summarization.  ...  Finally, we discuss applications of summarization on real-world graphs and conclude by describing some open problems in the field.  ...  Differences from Prior Surveys Previous work on surveying the graph summarization literature is scarce.  ... 
arXiv:1612.04883v3 fatcat:fhg2g5eldfdgfkzoqdmbfl5er4

A survey of graphs in natural language processing

VIVI NASTASE, RADA MIHALCEA, DRAGOMIR R. RADEV
2015 Natural Language Engineering  
We provide an overview of how Natural Language Processing problems have been projected into the graph framework, focusing in particular on graph construction – a crucial step in modeling the data to emphasize  ...  AbstractGraphs are a powerful representation formalism that can be applied to a variety of aspects related to language processing.  ...  They are relatively obvious when imagining words in a lexical resource or concepts in a knowledge network, or even words within a sentence that are connected to each other through what is formalized as  ... 
doi:10.1017/s1351324915000340 fatcat:knbsaqnd6ngahmv4m4tub32o6y
« Previous Showing results 1 — 15 out of 126,773 results