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.
Filters
A Generative Bayesian Graph Attention Network for Semi-Supervised Classification on Scarce Data
2021
2021 International Joint Conference on Neural Networks (IJCNN)
Preserved Fulltext
semi-supervised node classification tasks. ...
This research focuses on semi-supervised classification tasks, specifically for graph-structured data under datascarce situations. ...
Extensive graph neural network (GNN) based models, including graph convolution networks (GCNs) [3] and graph attention networks (GATs) [4] have been developed for unsupervised, semi-supervised and ...
doi:10.1109/ijcnn52387.2021.9533981
fatcat:r7bssnui4vgkpnt2jqzvcuspiy
Semi-AttentionAE: An Integrated Model for Graph Representation Learning
2021
IEEE Access
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.
More specifically, we integrate a supervised information extraction graph attention network to capture both node features and network structure, with an unsupervised feature extraction autoencoder to reduce ...
We conduct the node classification and visualization experiments on four real-world datasets, including two citation networks, one co-occurrence network, and one commodity network. ...
In Semi-AttentionAE, GAT samples the graph structure and node features, and generates input matrix H for AE through supervised learning based on node labels. ...
doi:10.1109/access.2021.3085114
fatcat:lppcn2gzrnhvnnuxvzi6ck63nu
Topological Feature Based Classification
[article]
2011
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Additionally, the model is shown to outperform graph-based semi-supervised methods on directed and approximately bipartite networks. ...
This work proposes a method, based on blockmodelling, for leveraging communities and other topological features for use in a predictive classification task. ...
The topological features which have received the most attention in recent years are communities or modules; groups of highly connected nodes within a globally sparse network. ...
arXiv:1110.4285v1
fatcat:nfzwdsspwvb5tfbt7tjk32w75m
Semi-Supervised Embedding of Attributed Multiplex Networks
2023
Proceedings of the ACM Web Conference 2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
The results show that our approach outperforms state-of-the-art methods for downstream tasks such as semi-supervised node classification and node clustering. ...
We propose a Semi-supervised Embedding approach for Attributed Multiplex Networks (SSAMN), to jointly embed nodes, node attributes, and node labels of multiplex networks in a low dimensional space. ...
HAN [41] is a semi-supervised graph neural network approach based on two attention-level mechanisms, hierarchical node-level, and metapathlevel attentions. ...
doi:10.1145/3543507.3583485
fatcat:rjaxhbifyrdo7cem63r7hnyc74
Graph Convolutional Architectures via Arbitrary Order of Information Aggregation
2020
IEEE Access
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.
INDEX TERMS Graph representation learning, graph convolutional networks, information aggregation, node classification. ...
Therefore, they have limitations in solving supervised machine learning tasks on networks. ...
respect to the semi-supervised node classification problem on networks. ...
doi:10.1109/access.2020.2995406
fatcat:i5son6436jdhfe6wg2zsqlxvhy
Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification
[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 study the problem of graph data augmentation for Graph Convolutional Network (GCN) in the context of improving the node embeddings for semi-supervised node classification. ...
Then, we propose an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embeddings. ...
[10] , which is the state-of-the-art model for semi-supervised node classification. ...
arXiv:2106.08848v1
fatcat:hplwajirorf7hcwtcxvqplufha
A Review of Joint Applications of IoT and Deep Learning
2023
IETI Transactions on Data Analysis and Forecasting (iTDAF)
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 2023; you can also visit the original URL.
The file type is application/pdf.
This paper also focuses on discussing the semi-supervised classification task of GCNs. ...
The innovative approach explored for innovative GCNs dealing with semi-supervised classification tasks lies in optimizing the GCN topology and using graph convolutional operations in the topological space ...
Therefore, progressive graph convolutional networks are a promising semi-supervised node classification method. ...
doi:10.3991/itdaf.v1i3.44517
fatcat:l2m5usrq55by5lzry7kgkfduxa
Adaptive Structural Fingerprints for Graph Attention Networks
2020
International Conference on Learning Representations
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.
Furthermore, our model provides a useful platform for different subspaces of node features and various scales of graph structures to "cross-talk" with each other through the learning of multi-head attention ...
Graph attention network (GAT) is a promising framework to perform convolution and massage passing on graphs. ...
On the theoretical side, we will borrow existing tools in semi-supervised learning and study the generalization performance of our approach on semi-supervised node embedding and classification. ...
dblp:conf/iclr/0001ZWZ20
fatcat:sz35ncjg35h2bcndd6quro7vsy
Influential Attributed Communities via Graph Convolutional Network (InfACom-GCN)
2022
Information
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.
as node classification and connection prediction. ...
The proposed approach contains two main steps: (1) Community detection using a graph convolutional network in a semi-supervised learning setting considering the correlation between attributes and the overall ...
The problem of semi-supervised community detection is then to label the remaining unlabeled nodes in G, and as a result form k communities of nodes. ...
doi:10.3390/info13100462
fatcat:ury24vikerdlbof2c3su2xo3qu
GrAMME: Semi-Supervised Learning using Multi-layered Graph Attention Models
[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.
Other Versions
In this paper, we consider the problem of semi-supervised learning with multi-layered graphs. Though deep network embeddings, e.g. ...
DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective. ...
We also thank Prasanna Sattigeri for the useful discussions, and sharing data. ...
arXiv:1810.01405v2
fatcat:gydvjhal4jfbfi24bvnbsrpr2u
SNEQ: Semi-Supervised Attributed Network Embedding with Attention-Based Quantisation
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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.
Our evaluation on four real-world networks of diverse characteristics shows that SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, node classification and node recommendation ...
In this paper, we present a novel semi-supervised network embedding and compression method, SNEQ, that is competitive with state-of-art embedding methods while being far more space- and time-efficient. ...
HCGE (Dos Santos, Piwowarski, and Gallinari 2016) is a supervised method for node classification with good improvement. ...
doi:10.1609/aaai.v34i04.5832
fatcat:gv42jo5cibc25cekyaed4jy7rm
Semi-supervised learning from imperfect data through particle cooperation and competition
2010
The 2010 International Joint Conference on Neural Networks (IJCNN)
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 2017; you can also visit the original URL.
The file type is application/pdf.
In spite of its importance, wrong label propagation in semi-supervised learning has received little attention from researchers. ...
In machine learning study, semi-supervised learning has received increasing interests in the last years. ...
Besides its importance and vast influence on classification, error propagation or semi-supervised learning from imperfect data has received little attention from researchers and there are only a few recent ...
doi:10.1109/ijcnn.2010.5596659
dblp:conf/ijcnn/BreveZQ10
fatcat:hu3zcirbx5hcja5hqnuxuty7ya
Semi-Supervised Node Classification by Graph Convolutional Networks and Extracted Side Information
[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 2020; 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:
2020 pre-print arXiv:2009.13734v1 fatcat:c7c5hqti45hqpcbevq4ewnpb3a
From this perspective, this paper revisits the node classification task in a semi-supervised scenario by graph convolutional networks (GCNs). ...
the node classification task. ...
dataset for the semi-supervised node classification. ...
arXiv:2009.13734v2
fatcat:tqk3kcb2abhc3igulyavifxuvi
Semi-supervised learning and graph neural networks for fake news detection
2019
Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
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.
To this extend, we opted for semi-supervised learning approaches. In particular, our work proposes a graph-based semi-supervised fake news detection method, based on graph neural networks. ...
Social networks have become the main platforms for information dissemination. ...
which nodes are relevant to the target node for classification. ...
doi:10.1145/3341161.3342958
dblp:conf/asunam/BenamiraDLRSM19
fatcat:llv66xw5bvcjbfb7n7ijb4s6ce
Community Detection-Based Feature Construction for Protein Sequence Classification
[chapter]
2015
Lecture Notes in Computer Science
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 2015; you can also visit the original URL.
The file type is application/pdf.
In prior work, we have proposed the use of a community detection approach to construct low dimensional feature sets for nucleotide sequence classification. ...
While this approach worked well for nucleotide sequence classification, it could not be directly used for protein sequences, as the Hamming distance is not a good measure for comparing short protein k-mers ...
cases for the semi-supervised scenario as well as for the domain adaptation scenario. ...
doi:10.1007/978-3-319-19048-8_28
fatcat:skiszp5tonavvowsacjztxgzqq
« Previous
Showing results 1 — 15 out of 17,628 results