462 Hits in 3.4 sec

Towards Unsupervised Deep Graph Structure Learning [article]

Yixin Liu, Yu Zheng, Daokun Zhang, Hongxu Chen, Hao Peng, Shirui Pan
2022 arXiv   pre-print
In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications.  ...  Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.  ...  Graph structure learning for robust graph neural networks. In Proceedings 2017. Community preserving network embedding.  ... 
arXiv:2201.06367v1 fatcat:ew3msx6p6vc5hadgkryoixhyuq

Deep Entity Classification: Abusive Account Detection for Online Social Networks

Teng Xu, Gerard Goossen, Huseyin Kerem Cevahir, Sara Khodeir, Yingyezhe Jin, Frank Li, Shawn Shan, Sagar Patel, David Freeman, Paul Pearce
2021 USENIX Security Symposium  
Our system: • Extracts "deep features" of accounts by aggregating properties and behavioral features from their direct and indirect neighbors in the social graph. • Employs a "multi-stage multi-task learning  ...  We leverage the insight that while accounts in isolation may be difficult to classify, their embeddings in the social graph-the network structure, properties, and behaviors of themselves and those around  ...  Recent works on graph neural networks (GNNs) [27, 33, 55] extend convolutional neural networks to perform node classifications.  ... 
dblp:conf/uss/XuGCKJ0SPFP21 fatcat:wyhi5w44pbgxhevntbly62ki74

Domain-adversarial Network Alignment [article]

Huiting Hong, Xin Li, Yuangang Pan, Ivor Tsang
2019 arXiv   pre-print
Specifically, we employ the graph convolutional networks to perform network embedding under the domain adversarial principle, given a small set of observed anchors.  ...  This paper proposes a unified deep architecture (DANA) to obtain a domain-invariant representation for network alignment via an adversarial domain classifier.  ...  Adversarial Training of Neural Networks Generative Adversarial Networks (GANs) [6] , which plays an adversarial minimax game between the generator and discriminator, frees the users from the painful practice  ... 
arXiv:1908.05429v1 fatcat:hupxtj4r2rh7pburrj5ymfj6ci

Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality [article]

Jaybie A. de Guzman, Kanchana Thilakarathna, Aruna Seneviratne
2020 arXiv   pre-print
objects or surfaces, often including their structural (i.e. spatial geometry) and photometric (e.g. color, and texture) attributes, to allow applications to place virtual or synthetic objects seemingly "anchored  ...  We designed an adversary that builds up on existing place and shape recognition methods over 3D data as attackers to which the proposed spatial privacy approach can be evaluated against.  ...  ADVERSARIAL SPATIAL INFERENCE We utilize two methods for our spatial inference attack: a descriptor nearest-neighbor matching approach we call NN-matcher (improved from [7] ), and a deep neural network  ... 
arXiv:2004.08029v1 fatcat:trg33dzvdrg4jcgc4ojz3f35hy

Adversarial Attacks on Face Detectors Using Neural Net Based Constrained Optimization

Avishek Joey Bose, Parham Aarabi
2018 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)  
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a  ...  In this thesis, we propose a novel strategy to craft adversarial examples by solving a constrained optimization problem using an adversarial generator network.  ...  Neural Networks Neural networks are modeled as a collection of neurons stacked together in layers forming an acyclic graph.  ... 
doi:10.1109/mmsp.2018.8547128 dblp:conf/mmsp/BoseA18 fatcat:lochow2euzbyvg2l3eonjgo43u

A Survey on Deep Semi-supervised Learning [article]

Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu
2021 arXiv   pre-print
We first present a taxonomy for deep semi-supervised learning that categorizes existing methods, including deep generative methods, consistency regularization methods, graph-based methods, pseudo-labeling  ...  ReMixMatch [72] extends MixMatch [71] by introducing distribution alignment and augmentation anchoring.  ...  as deep neural networks.  ... 
arXiv:2103.00550v2 fatcat:lymncf5wavgkhaenbvqlyvhuaa

Deep Learning for Free-Hand Sketch: A Survey [article]

Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang
2022 arXiv   pre-print
parameters set manually Abbreviated Terms Descriptions CNN convolutional neural network GNN graph neural network GCN graph convolutional network RNN recurrent neural network LSTM Long Short Term Memory  ...  [21] , adversarial sketch based image editing [22] , graph neural network based sketch recognition [23] , graph convolution-based sketch semantic segmentation [24] , and sketch based software prototyping  ... 
arXiv:2001.02600v3 fatcat:lek5sivzsrat3i52lqh2eifnia

Deep Learning for 3D Point Cloud Understanding: A Survey [article]

Haoming Lu, Humphrey Shi
2021 arXiv   pre-print
While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points.  ...  Besides, Point-GNN [91] proposed a single-shot method based on graph neural networks. It first builds a fixed radius near-neighbors graph over the input point cloud.  ...  Graph networks Graph networks consider a point cloud as a graph and the vertices of the graph as the points, and edges are generated based on the neighbors of each point.  ... 
arXiv:2009.08920v2 fatcat:qiuhs6v345bpffzjk2nvhgbfvq

Long Short-Term Relation Networks for Video Action Detection [article]

Dong Li and Ting Yao and Zhaofan Qiu and Houqiang Li and Tao Mei
2020 arXiv   pre-print
LSTR then models short-term human-context interactions within each clip through spatio-temporal attention mechanism and reasons long-term temporal dynamics across video clips via Graph Convolutional Networks  ...  Technically, Region Proposal Networks (RPN) is remoulded to first produce 3D bounding boxes, i.e., tubelets, in each video clip.  ...  Specifically, Tubelet Proposal Networks (TPN) remoulds Region Proposal Networks (RPN) by extending 2D anchor boxes in RPN to 3D anchor tubelets, and is first exploited to produce human actor tubelets in  ... 
arXiv:2003.14065v1 fatcat:lam2eqnyrjadzgibz4vlcpmyc4

Network representation learning: models, methods and applications

Anuraj Mohan, K. V. Pramod
2019 SN Applied Sciences  
Terminologies and problem definition Definition 1 A Network is a graph is the set of vertices and e ∈ E is an edge between any two vertices.  ...  A significant amount of research effort is made in the past few years to generate node representations from graph-structured data using representation learning methods.  ...  ] , deep convolutional neural networks (CNN) [60] , long short-term memory networks (LSTM) [41] , and generative adversarial networks (GAN) [37] .  ... 
doi:10.1007/s42452-019-1044-9 fatcat:zvlbj4qozzfw3dxoyevb6wgska

A survey in Adversarial Defences and Robustness in NLP [article]

Shreya Goyal, Sumanth Doddapaneni, Mitesh M.Khapra, Balaraman Ravindran
2022 arXiv   pre-print
In recent years, it has been seen that deep neural networks are lacking robustness and are likely to break in case of adversarial perturbations in input data.  ...  These methods are not just used for defending neural networks from adversarial attacks, but also used as a regularization mechanism during training, saving the model from overfitting.  ...  In the work [121] , authors have presented an exhaustive survey on adversarial attacks on deep neural networks for images, text, and graphs.  ... 
arXiv:2203.06414v2 fatcat:2ukd44px35e7ppskzkaprfw4ha

Multiplex Network Embedding Model with High-Order Node Dependence

Nianwen Ning, Qiuyue Li, Kai Zhao, Bin Wu, Shenghua Liu
2021 Complexity  
Multiplex networks have been widely used in information diffusion, social networks, transport, and biology multiomics.  ...  In the intralayer embedding phase, we present a symmetric graph convolution-deconvolution model to embed high-order proximity information as the intralayer embedding of nodes in an unsupervised manner.  ...  Graph Neural Network-Based Methods.  ... 
doi:10.1155/2021/6644111 fatcat:qsxs4kyoqrgv5ne2xpuns4qsru

An Attentive Survey of Attention Models [article]

Sneha Chaudhari, Varun Mithal, Gungor Polatkan, Rohan Ramanath
2021 arXiv   pre-print
Attention Model has now become an important concept in neural networks that has been researched within diverse application domains.  ...  We also describe how attention has been used to improve the interpretability of neural networks. Finally, we discuss some future research directions in attention.  ...  Memory Network Architectures Fig. 7 . 7 Neighbor importance in Graph Convolutional Network vs Graph Attention Network. Figure from  ... 
arXiv:1904.02874v3 fatcat:fyqgqn7sxzdy3efib3rrqexs74

When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)

Victor Villena-Martinez, Sergiu Oprea, Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo, Robert B. Fisher
2020 Applied Sciences  
Deep Registration Networks (DRNs) are those architectures trying to solve the alignment task using a learning algorithm.  ...  In a similar way to humans, neural networks are able to understand the input data by extracting an abstract understanding of it [82] .  ...  of abstraction.  ... 
doi:10.3390/app10217524 fatcat:zevtfrfsuzhyliknzg5thaprbq

Graph convolutional networks: a comprehensive review

Si Zhang, Hanghang Tong, Jiejun Xu, Ross Maciejewski
2019 Computational Social Networks  
In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent  ...  Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems.  ...  Message-Passing Neural Networks (MPNNs) proposed in [69] generalize many variants of graph neural networks, such as graph convolutional networks (e.g., [37, 56, 61] ) and gated graph neural networks  ... 
doi:10.1186/s40649-019-0069-y fatcat:usvlugxj6jcrzesm7dthrecp3m
« Previous Showing results 1 — 15 out of 462 results