Filters








760 Hits in 3.0 sec

Motif-Aware Adversarial Graph Representation Learning

Ming Zhao, Yinglong Zhang, Xuewen Xia, Xing Xu
2022 IEEE Access  
In this paper, for undirected graphs, we present a novel Motif-Aware Generative Adversarial Network (MotifGAN) model to learn graph representation based on a re-weighted graph, which unifies both the Motif  ...  INDEX TERMS Graph representation learning, higher order structure, motif connectivity, generative adversarial networks.  ...  To address the aforementioned problems, in this paper, we propose Motif-Aware Adversarial Graph Representation Learning (MotifGAN).  ... 
doi:10.1109/access.2022.3144233 fatcat:lsbfu7ov2rakhhqwlpad6lvmw4

CommunityGAN: Community Detection with Generative Adversarial Nets [article]

Yuting Jia, Qinqin Zhang, Weinan Zhang, Xinbing Wang
2019 arXiv   pre-print
With the recent development of deep learning, graph representation learning techniques are also utilized for community detection.  ...  In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning.  ...  Moreover, Generative Adversarial Nets (GAN) has also been introduced for learning better graph representation [25] .  ... 
arXiv:1901.06631v3 fatcat:qsljeklsbbeutjak3rp3pzbrne

Anomaly Mining – Past, Present and Future [article]

Leman Akoglu
2021 arXiv   pre-print
In this article, I focus on two areas, (1) point-cloud and (2) graph-based anomaly mining.  ...  representation learning that is better suitable for OD.  ...  The most recent trend is representation learning or graph embedding through graph neural networks (GNNs) [Hamilton et al., 2017] .  ... 
arXiv:2105.10077v2 fatcat:znvvz6ewpbdpjhnhp35kudvzlu

A Survey on the Recent Advances of Deep Community Detection

Stavros Souravlas, Sofia Anastasiadou, Stefanos Katsavounis
2021 Applied Sciences  
Most of the community detection techniques are based on graph structures. In this paper, we present the recent advances of deep learning techniques for community detection.  ...  The Graph AGM generates the most likely motifs with graph structure awareness. Not easy to infer due to random walk involved in the design of the AGM.  ...  More specifically, the Class-Imbalanced Convolution Learning is a two-layer graph convolutional network, which is used for learning the node-level representation on the input graph.  ... 
doi:10.3390/app11167179 fatcat:lzff6bskjrfgfo5ho7dalltke4

Enhancing Social Recommendation with Adversarial Graph Convolutional Networks [article]

Junliang Yu, Hongzhi Yin, Jundong Li, Min Gao, Zi Huang, Lizhen Cui
2020 arXiv   pre-print
In this paper we propose a deep adversarial framework based on graph convolutional networks (GCN) to address these problems.  ...  Finally, we adopt adversarial training to unify all the components by playing a Minimax game and ensure a coordinated effort to enhance recommendation performance.  ...  [36] developed a dual graph attention networks to collaboratively learn representations for two-fold social effects.  ... 
arXiv:2004.02340v4 fatcat:2fg4c4c3kbdvnhu4rf32ssrglu

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
Graph Neural Networks (GNNs) have made rapid developments in the recent years.  ...  Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal  ...  Reinforcement learning is also applied in graph structure learning for robust representation learning [190] .  ... 
arXiv:2204.08570v1 fatcat:7c3pkxitrbhgxj6fytn6f3r644

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection [article]

Bingzhe Wu, Jintang Li, Junchi Yu, Yatao Bian, Hengtong Zhang, CHaochao Chen, Chengbin Hou, Guoji Fu, Liang Chen, Tingyang Xu, Yu Rong, Xiaolin Zheng (+8 others)
2022 arXiv   pre-print
In contrast to conventional graph learning research which mainly cares about model performance, TwGL considers various reliability and safety aspects of the graph learning framework including but not limited  ...  Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint.  ...  Introduction Recently, Deep Graph Learning (DGL) based on Graph Neural Networks (GNNs) have emerged as a powerful learning paradigm for graph representation learning.  ... 
arXiv:2205.10014v2 fatcat:aobv34rwg5ehpka4fsuar2gm7i

Analyzing Data-Centric Properties for Contrastive Learning on Graphs [article]

Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, Jayaraman J. Thiagarajan
2022 arXiv   pre-print
Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semantics, separability of classes  ...  This raises the question: how do graph SSL methods, such as contrastive learning (CL), work well?  ...  Self-Supervised Graph Representation Learning.  ... 
arXiv:2208.02810v1 fatcat:223psynefjdclluv7xba6fstdy

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders.  ...  Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.  ...  CANE: community-aware network embedding via adversarial CANE Community-Aware Network Embedding [97] training Graph Convolutional Neural Networks with CayleyNets: Graph convolutional neural networks  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

Deep learning for inferring transcription factor binding sites

Peter K. Koo, Matt Ploenzke
2020 Current Opinion in Systems Biology  
Despite their high predictive accuracy, there are no guarantees that a high-performing deep learning model will learn causal sequence-function relationships.  ...  Deep learning is a powerful tool for predicting transcription factor binding sites from DNA sequence.  ...  Hence, filter analysis should 120 only be employed when a model is explicitly trained to learn interpretable motif representations.  ... 
doi:10.1016/j.coisb.2020.04.001 pmid:32905524 pmcid:PMC7469942 fatcat:eaesypmqjfflbjgjeja7kenpye

Deep Graph Generators: A Survey

Faezeh Faez, Yassaman Ommi, Mahdieh Soleymani Baghshah, Hamid R. Rabiee
2021 IEEE Access  
Thanks to the advances in graph-based deep learning, and in particular graph representation learning, deep graph generation methods have recently emerged with new applications ranging from discovering  ...  , adversarial, and flow-based graph generators, providing the readers a detailed description of the methods in each class.  ...  Beyond the prominent field of graph representation learning, graph-related research further includes other areas such as graph matching [7] , [8] , adversarial attack and defense on graph-based neural  ... 
doi:10.1109/access.2021.3098417 fatcat:6xzg5cs75zhovdbpjkignfr3xu

Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues [article]

Shanu Kumar, Shubham Atreja, Anjali Singh, Mohit Jain
2019 arXiv   pre-print
We present a novel approach for adversarial training of existing scene graph models that enables the use of scene graphs for new applications in the absence of any labelled training data.  ...  In this work, given an image, we propose to generate a Civic Issue Graph consisting of a set of objects and the semantic relations between them, which are representative of the underlying civic issue.  ...  Without adversarial training, the model has not learned the representation for any unseen pair of objects from the civic domain and will not be able to predict such relations (R n ).  ... 
arXiv:1901.10124v1 fatcat:lud55b3uofahpc5ww62qzu5kry

2021 Index IEEE Transactions on Knowledge and Data Engineering Vol. 33

2022 IEEE Transactions on Knowledge and Data Engineering  
Chen, D., +, TKDE Feb. 2021 569-584 Learning Graph Representation With Generative Adversarial Nets. Metagraph-Based Learning on Heterogeneous Graphs.  ...  Dautov, R., +, TKDE Jan. 2021 55-69 Minimax techniques Learning Graph Representation With Generative Adversarial Nets.  ...  Generalization (artificial intelligence) Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-Label Learning.  ... 
doi:10.1109/tkde.2021.3128365 fatcat:4m5kefreyrbhpb3lhzvgqzm3qu

Text Data Augmentation for Deep Learning

Connor Shorten, Taghi M. Khoshgoftaar, Borko Furht
2021 Journal of Big Data  
We follow these motifs with a concrete list of augmentation frameworks that have been developed for text data.  ...  AbstractNatural Language Processing (NLP) is one of the most captivating applications of Deep Learning.  ...  Acknowledgements We would like to thank the reviewers in the Data Mining and Machine Learning Laboratory at Florida Atlantic University.  ... 
doi:10.1186/s40537-021-00492-0 fatcat:bcbaqkpicnd6dcwc34pdijosby

Structure-Aware Hierarchical Graph Pooling using Information Bottleneck [article]

Kashob Kumar Roy, Amit Roy, A K M Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali
2021 arXiv   pre-print
Besides, they are prone to adversarial attacks.  ...  For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph.  ...  Furthermore, the structure-aware DiP-Readout function in HIBPool has more expressive potential to learn distinguishable representation for communities, even with homogeneous node features.  ... 
arXiv:2104.13012v1 fatcat:b3u7bakzrzatfadb3yz32ufjrq
« Previous Showing results 1 — 15 out of 760 results