Filters








863 Hits in 6.6 sec

A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications [article]

Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z. Li
2022 arXiv   pre-print
Then, we systematically categorize existing PGMs based on a taxonomy from four different perspectives. Next, we present the applications of PGMs in social recommendation and drug discovery.  ...  In this paper, we provide the first comprehensive survey for PGMs. We firstly present the limitations of graph representation learning and thus introduce the motivation for graph pre-training.  ...  In this paper, we present a survey to provide researchers a synthesis and pointer to related research on PGMs.  ... 
arXiv:2202.07893v2 fatcat:vidcathokrfibe53yuc3xaihzy

A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications [article]

Jun Xia, Yanqiao Zhu, Yuanqi Du, Stan Z. Li
2022
Then, we systematically categorize existing PGMs based on a taxonomy from four different perspectives. Next, we present the applications of PGMs in social recommendation and drug discovery.  ...  In this paper, we provide the first comprehensive survey for PGMs. We firstly present the limitations of graph representation learning and thus introduce the motivation for graph pre-training.  ...  Conclusions and Future Outlooks This paper is the first survey paper focusing on pretraining on graphs, which is one of the most popular research trend in GNNs community.  ... 
doi:10.48550/arxiv.2202.07893 fatcat:sybelun6trbklhwddnv64n7jym

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective [article]

Luis C. Lamb, Artur Garcez, Marco Gori, Marcelo Prates, Pedro Avelar, Moshe Vardi
2021 arXiv   pre-print
In this paper, we review the state-of-the-art on the use of GNNs as a model of neural-symbolic computing.  ...  Graph Neural Networks (GNN) have been widely used in relational and symbolic domains, with widespread application of GNNs in combinatorial optimization, constraint satisfaction, relational reasoning and  ...  Acknowledgements This work is partly supported by CNPq and CAPES, Brazil -Finance Code 001.  ... 
arXiv:2003.00330v7 fatcat:jiacrkwiuvbofnp5lmiemhn4ua

Graph Neural Networks: Methods, Applications, and Opportunities [article]

Lilapati Waikhom, Ripon Patgiri
2021 arXiv   pre-print
Taxonomy of each graph based learning setting is provided with logical divisions of methods falling in the given learning setting.  ...  This article provides a comprehensive survey of graph neural networks (GNNs) in each learning setting: supervised, unsupervised, semi-supervised, and self-supervised learning.  ...  Sato focuses more on the power of GNNs, and also presented a comprehensive overview of the powerful variants of GNNs, but has not focused on taxonomy.  ... 
arXiv:2108.10733v2 fatcat:j3rfmkiwenebvmfyboasjmx4nu

Graph Self-Supervised Learning: A Survey [article]

Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu
2022 arXiv   pre-print
Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies.  ...  We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL  ...  and applications of graph SSL.  ... 
arXiv:2103.00111v4 fatcat:y3zfg4ennnbnhhvmujd5rvltty

Self-Supervised Learning of Graph Neural Networks: A Unified Review [article]

Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhengyang Wang, Shuiwang Ji
2022 arXiv   pre-print
In this survey, we provide a unified review of different ways of training GNNs using SSL. Specifically, we categorize SSL methods into contrastive and predictive models.  ...  Our unified treatment of SSL methods for GNNs sheds light on the similarities and differences of various methods, setting the stage for developing new methods and algorithms.  ...  ACKNOWLEDGMENTS This work was supported in part by National Science Foundation grants IIS-2006861 and DBI-2028361, and National Institutes of Health grant 1R21NS102828.  ... 
arXiv:2102.10757v5 fatcat:mau6lbphw5hxjhc7oyejmo2zpu

Learning Graph Embeddings from

Andrey Kutuzov, Mohammad Dorgham, Oleksiy Oliynyk, Chris Biemann, Alexander Panchenko
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*  
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities.  ...  Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNetbased similarity measures, show that our approach yields competitive results, outperforming  ...  and HA 5851/2-1), which is part of the Priority Program Robust Argumentation Machines (RA-TIO) (SPP-1999), and Young Scientist Mobility Grant from the Faculty of Mathematics and Natural Sciences, University  ... 
doi:10.18653/v1/s19-1014 dblp:conf/starsem/KutuzovDOBP19 fatcat:uzgozi2dnbhyjgasx2i4256fge

Graph Neural Networks: A Review of Methods and Applications [article]

Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun
2021 arXiv   pre-print
In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research  ...  In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important  ...  In this paper, we provide a thorough review of different graph neural network models as well as a systematic taxonomy of the applications.  ... 
arXiv:1812.08434v6 fatcat:ncz44kny6nairjjnysrqd5qjoi

Spatio-Temporal Graph Contrastive Learning [article]

Xu Liu, Yuxuan Liang, Yu Zheng, Bryan Hooi, Roger Zimmermann
2021 arXiv   pre-print
We elaborate on four types of data augmentations, which disturb data in terms of graph structure, time domain, and frequency domain.  ...  However, existing graph contrastive learning methods cannot be directly applied to STG forecasting due to three reasons.  ...  According to the taxonomy from a recent survey , existing methods can be divided into cross-scale contrasting and same-scale contrasting.  ... 
arXiv:2108.11873v1 fatcat:ktkpm3m33fdr5lxglcmqcijpce

Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive [article]

Lirong Wu, Haitao Lin, Zhangyang Gao, Cheng Tan, Stan.Z.Li
2021 arXiv   pre-print
Deep learning on graphs has recently achieved remarkable success on a variety of tasks, while such success relies heavily on the massive and carefully labeled data.  ...  In this survey, we extend the concept of SSL, which first emerged in the fields of computer vision and natural language processing, to present a timely and comprehensive review of existing SSL techniques  ...  publicly available on platforms such as arxiv, OpenReview, etc.; (3) application methods, where graph SSL is only one of the adopted techniques or tricks and is not the focus of their works; (4) methods  ... 
arXiv:2105.07342v4 fatcat:iak3xwlx5nci3mlzerxhcylojm

Graph Neural Network for Traffic Forecasting: A Survey [article]

Weiwei Jiang, Jiayun Luo
2022 arXiv   pre-print
To the best of our knowledge, this paper is the first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems.  ...  In this survey, we review the rapidly growing body of research using different graph neural networks, e.g. graph convolutional and graph attention networks, in various traffic forecasting problems, e.g  ...  A taxonomy of existing traffic prediction methods, including both traditional and deep learning methods, is presented in [7] .  ... 
arXiv:2101.11174v4 fatcat:txrrk6yia5dcvcamabhqahsrni

Shape-Biased Domain Generalization via Shock Graph Embeddings [article]

Maruthi Narayanan, Vickram Rajendran, Benjamin Kimia
2021 arXiv   pre-print
The resulting graph and its descriptor is a complete representation of contour content and is classified using recent Graph Neural Network (GNN) methods.  ...  The inclusion of a role of shape alleviates these vulnerabilities and some approaches have achieved this by training on negative images, images endowed with edge maps, or images with conflicting shape  ...  Part of this research was conducted using computational resources and services at the Center for Computation and Visualization, Brown University.  ... 
arXiv:2109.05671v1 fatcat:hza4tljxcbcvhn4zzpzxmda2b4

A Survey on Visual Transfer Learning using Knowledge Graphs [article]

Sebastian Monka, Lavdim Halilaj, Achim Rettinger
2022 arXiv   pre-print
This survey focuses on visual transfer learning approaches using KGs.  ...  We provide a broad overview of knowledge graph embedding methods and describe several joint training objectives suitable to combine them with high dimensional visual embeddings.  ...  [166] provide a survey about reasoning mechanisms and knowledge integration methods for image understanding applications.  ... 
arXiv:2201.11794v1 fatcat:tapql5h4j5dvrnxjkaxek2cquu

Learning Graph Embeddings from WordNet-based Similarity Measures [article]

Andrey Kutuzov, Mohammad Dorgham, Oleksiy Oliynyk, Chris Biemann, Alexander Panchenko
2019 arXiv   pre-print
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities.  ...  Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming  ...  and HA 5851/2-1), which is part of the Priority Program Robust Argumentation Machines (RA-TIO) (SPP-1999), and Young Scientist Mobility Grant from the Faculty of Mathematics and Natural Sciences, University  ... 
arXiv:1808.05611v4 fatcat:mrb36kdyabapzgnl4r3wtmcmt4

Benchmarking Node Outlier Detection on Graphs [article]

Kay Liu, Yingtong Dou, Yue Zhao, Xueying Ding, Xiyang Hu, Ruitong Zhang, Kaize Ding, Canyu Chen, Hao Peng, Kai Shu, Lichao Sun, Jundong Li (+3 others)
2022 arXiv   pre-print
Despite the proliferation of algorithms developed in recent years, the lack of a standard and unified setting for performance evaluation limits their advancement and usage in real-world applications.  ...  on real-world datasets; (3) comparing the efficiency and scalability of the algorithms by runtime and GPU memory usage on synthetic graphs at different scales.  ...  Although UNOD focuses on unsupervised detection methods due to the abundance of applications, there can be cases with a small set of labels (either for OD or relevant tasks) available in graph applications  ... 
arXiv:2206.10071v1 fatcat:icapq3qi3zfblhvg7nerof7fzy
« Previous Showing results 1 — 15 out of 863 results