Filters








1,389 Hits in 3.0 sec

Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems [article]

Lianghao Xia, Chao Huang, Yong Xu, Huance Xu, Xiang Li, Weiguo Zhang
2022 arXiv   pre-print
into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks.  ...  To address the issues, we develop a Collaborative Reflection-Augmented Autoencoder Network (CRANet), that is capable of exploring transferable knowledge from observed and unobserved user-item interactions  ...  [22] develops a neural network-based approach to use the inferred imputed values for learning user preference. Wan et al.  ... 
arXiv:2201.03158v1 fatcat:qm4pposhvfa4ligy5prsvj7fxa

Front Matter: Volume 12260

Yingfa Lu, Changbo Cheng
2022 International Conference on Computer Application and Information Security (ICCAIS 2021)  
Please use the following format to cite material from these proceedings: Author(s), "Title of Paper," in International Conference on Computer Application and Information Security (ICCAIS 2021), edited  ...  approach for credit scoring based on sequential pattern mining [12260-83] 0C A traffic data imputing method based on multisource recurrent neural network [12260-104] 0D A self-adaptive loop matching algorithm  ...  based on GA for 2D lidar SLAM [12260-108] 0E Skeleton-based one-shot action recognition on graph neural network [12260-102] 0F Spatio-temporal multi-attention graph network for traffic forecasting [12260  ... 
doi:10.1117/12.2642187 fatcat:mtiohaetmfcm3eds6qgtfrnpbe

Explainable Deep Modeling of Tabular Data using TableGraphNet [article]

Gabriel Terejanu, Jawad Chowdhury, Rezaur Rashid, Asif Chowdhury
2020 arXiv   pre-print
Our approach learns a graph representation for each record in the dataset.  ...  Attribute centric features are then derived from the graph and fed into a contribution deep set model to produce the final predictions.  ...  Graph representations using distance neural networks.  ... 
arXiv:2002.05205v1 fatcat:vdw34szsrjg63bst3egik7zulu

Modeling electronic health record data using a knowledge-graph-embedded topic model [article]

Yuesong Zou, Ahmad Pesaranghader, Aman Verma, David Buckeridge, Yue Li
2022 arXiv   pre-print
KG-ETM distills latent disease topics from EHR data by learning the embedding from the medical knowledge graphs. We applied KG-ETM to a large-scale EHR dataset consisting of over 1 million patients.  ...  We evaluated its performance based on EHR reconstruction and drug imputation. KG-ETM demonstrated superior performance over the alternative methods on both tasks.  ...  To learn the node embedding, we used a graph attention networks (GATs) [10] (Figure 1c ).  ... 
arXiv:2206.01436v1 fatcat:kdaipn7alvfa5lcwlzcfoqfnhq

2020 Index IEEE Transactions on Knowledge and Data Engineering Vol. 32

2021 IEEE Transactions on Knowledge and Data Engineering  
., +, TKDE June 2020 1179-1198 Multilayer perceptrons Feature Selection for Neural Networks Using Group Lasso Regularization.  ...  Shang, F., +, TKDE Jan. 2020 188-202 Convex programming Feature Selection for Neural Networks Using Group Lasso Regularization.  ... 
doi:10.1109/tkde.2020.3038549 fatcat:75f5fmdrpjcwrasjylewyivtmu

Handling Missing Data with Graph Representation Learning [article]

Jiaxuan You, Xiaobai Ma, Daisy Yi Ding, Mykel Kochenderfer, Jure Leskovec
2020 arXiv   pre-print
These tasks are then solved with Graph Neural Networks.  ...  GRAPE tackles the missing data problem using a graph representation, where the observations and features are viewed as two types of nodes in a bipartite graph, and the observed feature values as edges.  ...  GRAPE solves both tasks via Graph Neural Networks (GNNs).  ... 
arXiv:2010.16418v1 fatcat:i5uxtsxfabhajlfvp4fyke53lq

Relational VAE: A Continuous Latent Variable Model for Graph Structured Data [article]

Charilaos Mylonas, Imad Abdallah, Eleni Chatzi
2021 arXiv   pre-print
Graph Networks (GNs) enable the fusion of prior knowledge and relational reasoning with flexible function approximations.  ...  To that end, we combine complementary pre-existing approaches on VB for graph data and propose an approach that relies on graph-structured latent and conditioning variables.  ...  Introduction Graph Neural Networks (GNNs) [12, 2] have been established as an effective tool for representation learning on graph structured data.  ... 
arXiv:2106.16049v1 fatcat:t3qa5n2eazgvnn32y3677ioyhe

Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion [article]

Anthony Bourached, Robert Gray, Xiaodong Guan, Ryan-Rhys Griffiths, Ashwani Jha, Parashkev Nachev
2022 arXiv   pre-print
Here we propose a novel architecture based on hierarchical variational autoencoders and deep graph convolutional neural networks for generating a holistic model of action over multiple time-scales.  ...  We show this Hierarchical Graph-convolutional Variational Autoencoder (HG-VAE) to be capable of generating coherent actions, detecting out-of-distribution data, and imputing missing data by gradient ascent  ...  Graph convolutions: Graph neural networks Kipf and Welling [2016] have received increasing attention in recent years.  ... 
arXiv:2111.12602v4 fatcat:h6txxzdqmndidmkubplxv47alu

Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation [article]

Arushi Goel, Basura Fernando, Frank Keller, Hakan Bilen
2022 arXiv   pre-print
Our model-agnostic training procedure imputes missing informative relations for less informative samples in the training data and trains a SGG model on the imputed labels along with existing annotations  ...  Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding.  ...  Broadly, recent advances in SGG have been obtained by extracting local and global visual features in convolutional neural networks [23, 45, 68] or graph neural networks [31, 56, 61] combined with language  ... 
arXiv:2111.13517v2 fatcat:j4idc2jwr5gjpk5szeqcov76mm

Learning to Impute: A General Framework for Semi-supervised Learning [article]

Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen
2020 arXiv   pre-print
In this paper, we take a more direct approach for semi-supervised learning and propose learning to impute the labels of unlabeled samples such that a network achieves better generalization when it is trained  ...  Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their  ...  Learning to impute efficiently.  ... 
arXiv:1912.10364v3 fatcat:xdgwywrfcveutiqogurcczbf4q

A Gender-Neutral Approach to Detect Early Alzheimer's Disease Applying a Three-layer NN

Shithi Maitra, Tonmoy Hossain, Abdullah Al-Sakin, Sheikh Inzamamuzzaman, Md. Mamun, Syeda Shabnam
2019 International Journal of Advanced Computer Science and Applications  
The significance of this work consists in endorsing educational, socio-economic factors as useful features and eliminating the gender-bias using a simple neural network model without the need for complete  ...  MRI tuples that can be compensated for using specialized imputation methods.  ...  The recent bio-medical researches are gaining momentum using Neural Networks (NN).  ... 
doi:10.14569/ijacsa.2019.0100368 fatcat:b7ilf3ouo5hdzju6zvpjasz7yy

Emerging Artificial Intelligence Applications in Spatial Transcriptomics Analysis [article]

Yijun Li, Stefan Stanojevic, Lana X. Garmire
2022 arXiv   pre-print
Such advancement comes with the urgent need for novel computational methods to handle the unique challenges of ST data analysis.  ...  DSTG [43] is a semi-supervised method for deconvolving ST data. DSTG uses a graph convolutional neural network model. DSTG uses scRNA-Seq data and ST data as input.  ...  DeepSpaCE [55] is a semi-supervised learning method that imputes spatial gene expression from H&E images and enhances the resolution of ST data using convolutional neural networks.  ... 
arXiv:2203.09664v1 fatcat:om6cen2vsrai3jgrkrvolxpg3q

Generative Adversarial Networks for Spatio-temporal Data: A Survey [article]

Nan Gao, Hao Xue, Wei Shao, Sichen Zhao, Kyle Kai Qin, Arian Prabowo, Mohammad Saiedur Rahaman, Flora D. Salim
2021 arXiv   pre-print
Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation.  ...  Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images in the computer vision area.  ...  With the prevalence of deep learning, many neural networks (e.g., Convolutional Neural Network (CNN) [81] , Recurrent Neural Network (RNN) [109] , Autoencoder (AE) [66] , Graph Convolutional Nevertheless  ... 
arXiv:2008.08903v3 fatcat:pbhxbfgw65bodksjdmwazwo4dq

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

2022 IEEE Transactions on Knowledge and Data Engineering  
., +, TKDE Jan. 2021 55-69 Efficient Distributed k-Clique Mining for Large Networks Using MapReduce.  ...  ., +, TKDE March 2021 921-934 Efficient Distributed k-Clique Mining for Large Networks Using MapReduce.  ... 
doi:10.1109/tkde.2021.3128365 fatcat:4m5kefreyrbhpb3lhzvgqzm3qu

Data Augmentation for Deep Graph Learning: A Survey [article]

Kaize Ding, Zhe Xu, Hanghang Tong, Huan Liu
2022 arXiv   pre-print
Graph neural networks, as powerful deep learning tools to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks.  ...  To counter the data noise and data scarcity issues in deep graph learning (DGL), increasing graph data augmentation research has been conducted lately.  ...  As a powerful deep learning tool to model graphstructured data, graph neural networks (GNNs) which generally follow a recursive message-passing scheme, have drawn a surge of research interests lately.  ... 
arXiv:2202.08235v1 fatcat:5jutv3soenfh3ikbrgeckeynw4
« Previous Showing results 1 — 15 out of 1,389 results