A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
In this paper, we develop a graph-based convolutional network for learning on multi-view networks. ...
We show that this method outperforms state-of-the-art semi-supervised learning algorithms on three different prediction tasks using mobile phone datasets from three different developing countries. ...
Multi-GCN: Multi-View Graph Convolutional Networks Our approach to semi-supervised learning on multi-view graphs integrates three steps, depicted in Figure 1 . ...
doi:10.1609/aaai.v33i01.3301606
fatcat:uztoujvgonajtoqeqp2pahthyu
Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we develop a graph-based convolutional network for learning on multi-view networks. ...
We show that this method outperforms state-of-the-art semi-supervised learning algorithms on three different prediction tasks using mobile phone datasets from three different developing countries. ...
Multi-GCN: Multi-View Graph Convolutional Networks Our approach to semi-supervised learning on multi-view graphs integrates three steps, depicted in Figure 1 . ...
arXiv:1901.11213v1
fatcat:eu75x365sjbnrhov3znbovaqdq
Adversarial Semi-supervised Learning for Corporate Credit Ratings
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2104.02479v1 fatcat:tx5utig7abhyddfqvycredalbi
Then in the second phase, adversarial semi-supervised learning is applied uniting labeled data and pseudo-labeled data. ...
Specifically, we consider the problem of adversarial semi-supervised learning (ASSL) for corporate credit rating which has been rarely researched before. ...
All authors had approved the final version Acknowledgment This work is jointly supported by National Natural Science Foundation of China (62071017) and Major Projects in Tianjin Binhai New District (BHXQKJXM-PT-ZKZNSBY ...
arXiv:2104.02479v2
fatcat:hgnqbyc5krabtnrfnw2kvlirme
Research on the Application of Machine Learning Algorithms in Credit Risk Assessment of Minor Enterprises
2021
Converter
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In order to understand the function of machine learning algorithms in predicting enterprise credit risk, the research designs five models, including Logistic Regression, Decision Tree, Naïve Bayesian, ...
Experiments show that machine learning algorithms have high accuracy for both large-scale data and small-scale data. ...
Li et al. used multi-layer perceptron and radial basis functions to evaluate the credit of minor enterprises in the P2P online lending platform and multi-layer perceptron can better predict defaulting ...
doi:10.17762/converter.220
fatcat:miafkis7vzcwpjfe4kzym36wi4
Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our architecture represents agent communication through graph convolution and applies an existing credit assignment structure, counterfactual multi-agent policy gradient (COMA), to assist agents to learn ...
We evaluate our method on a range of tasks, demonstrating the advantage of marrying communication with credit assignment. ...
Communication Module We now describe our multi-agent communication architecture in details. Our communication kernel consists of graph convolutions and relation kernels. ...
arXiv:2004.00470v2
fatcat:4jzk2hjmxzempnjs5wfwn5lgci
Deep Convolutional Clustering-Based Time Series Anomaly Detection
2021
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The system solely relies on unlabeled data and employs a 1D-convolutional neural network-based deep autoencoder architecture. ...
This paper presents a novel approach for anomaly detection in industrial processes. ...
the number of convolution kernels in the given layer. ...
doi:10.3390/s21165488
pmid:34450930
pmcid:PMC8400863
fatcat:6bk4djhthnd2bbx7kvb4gnxyxa
Survey on Semantic Segmentation using Deep Learning Techniques
2019
Neurocomputing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In addition, we present the common evaluation matrix used to measure their accuracy. ...
Many of these methods have been built using the deep learning paradigm that has shown a salient performance. ...
They introduced an additional convolution with a kernel size of 3 × 3 before the first convolution layer in ResNet, which enables the network to learn more high resolution features in less time. ...
doi:10.1016/j.neucom.2019.02.003
fatcat:aelsfl7unvdw5j2rtyqhtgqrsm
An Introduction to Robust Graph Convolutional Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a novel Robust Graph Convolutional Neural Networks for possible erroneous single-view or multi-view data where data may come from multiple sources. ...
By incorporating an extra layers via Autoencoders into traditional graph convolutional networks, we characterize and handle typical error models explicitly. ...
For supervised learning, = 0, while for semi-supervised learning, > 0.
Model Architecture To alleviate sensitivity of GCN against error in data, we utilize robust autoencoder. ...
arXiv:2103.14807v1
fatcat:52zu625fdve4ln3oxwjxjxlea4
Identification of Fake vs. Real Identities on Social Media using Random Forest and Deep Convolutional Neural Network
2019
International Journal of Engineering and Advanced Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Identity detection is very essential in social media platforms, various platform has facing fake accounts influence since couple of years in current eras. ...
LITERATURE SURVEY In machine learning, classification is based on learning from training database. This learning can be categorized into three types as: supervised, semi-supervised and unsupervised. ...
Semi-supervised method of learning is a combination of both supervised and unsupervised learning where some of the class labels are known. ...
doi:10.35940/ijeat.a9739.109119
fatcat:lduxxk3m7jfzbo7dxaavs2trfa
Financial Fraud Detection Using Deep Learning Based on Modified Tabular Learning
[chapter]
2022
Proceedings of the 2022 3rd International Conference on E-commerce and Internet Technology (ECIT 2022)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
However, these methods are not interpretable in tabular data model, we proposed a feature-based deep learning regression model that can directly deal with tabular data. ...
At present, the mainstream intelligent methods for fraud detection include convolutional neural network (CNN) and support vector regression (SVR). ...
Provides an end-to-end learning approach based on gradient descent with the benefit of semi-supervised learning and the ability to use information from another training model to learn to solve related ...
doi:10.2991/978-94-6463-005-3_55
fatcat:2nbndvr6brd43kfbypqqbkp5f4
On the Use of High-Order Feature Propagation in Graph Convolution Networks with Manifold Regularization
2021
Information Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Graph Convolutional Networks (GCNs) have received a lot of attention in pattern recognition and machine learning. ...
While manifold regularization can add additional information, the GCN-based semi-supervised classification process cannot consider the full layer-wise structured information. ...
Acknowledgments This work is supported in part by the University of the Basque Country UPV/EHU grant GIU19/027. ...
doi:10.1016/j.ins.2021.10.041
fatcat:d5pqj722cnbuxarujyeteelu2i
CogDL: A Toolkit for Deep Learning on Graphs
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Deep learning on graphs has attracted tremendous attention from the graph learning community in recent years. ...
In CogDL, we propose a unified design for the training loop of graph neural network (GNN) models, making it unique among existing graph learning libraries. ...
The datasets consist of two parts, including both semi-supervised and fully-supervised settings. • Semi-supervised datasets include three citation networks, Citeseer, Cora, and Pubmed [29] . ...
arXiv:2103.00959v3
fatcat:34lxb53rxjb2hnx5ramu5nomdq
Improving automatic segmentation of liver tumor images using a deep learning model
2024
Heliyon
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Then, multi-resolution deep supervision is introduced in the network, resulting in more robust segmentation. ...
In response to this demand, the current paper advocates a liver vessel segmentation approach that employs an enhanced 3D fully convolutional neural network V-Net. ...
to reduce information loss. (2) Introduce multi-resolution deep supervision in the network, and divide the liver blood vessels into multi-resolution feature maps, which is regarded as multi-task learning ...
doi:10.1016/j.heliyon.2024.e28538
pmid:38571625
pmcid:PMC10988037
fatcat:lfca6267fvcb5hkv6leevzrqp4
MF-Net: Multi-Scale Information Fusion Network for CNV Segmentation in Retinal OCT Images
2021
Frontiers in Neuroscience
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In addition, to leverage unlabeled data to further improve the CNV segmentation, a semi-supervised version of MF-Net is designed based on pseudo-label data augmentation strategy, which can leverage unlabeled ...
Although many deep learning-based methods have achieved promising results in many medical image segmentation tasks, CNV segmentation in retinal optical coherence tomography (OCT) images is still very challenging ...
The details for data strategies are listed in Table 1 .
Supervised Semi-supervised Training Retinal OCT images with ground truth from three folds. ...
doi:10.3389/fnins.2021.743769
pmid:34690681
pmcid:PMC8533052
fatcat:4oxs57do55f4foqynu75xdskxa
Accurate Tumor Segmentation via Octave Convolution Neural Network
2021
Frontiers in Medicine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose an effective and efficient method for tumor segmentation in liver CT images using encoder-decoder based octave convolution networks. ...
More importantly, we introduce a deep supervision mechanism during the learning process to combat potential optimization difficulties, and thus the model can acquire a much faster convergence rate and ...
FIGURE 2 | 2 The octave convolution kernel. k × k octave convolution kernel W is equivalent to vanilla convolution kernel because they have exactly the same number of parameters. ...
doi:10.3389/fmed.2021.653913
pmid:34095168
pmcid:PMC8169966
fatcat:bqlgbbnhqvc3blskhgrzha62mm
« Previous
Showing results 1 — 15 out of 1,252 results