Results 31 to 40 of about 9,194 (254)

RARE: Robust Masked Graph Autoencoder

CoRR, 2023
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important ...
Wenxuan Tu, Qing Liao 0001, Sihang Zhou 0001, Xin Peng 0010, Chuan Ma 0001, Zhe Liu 0001, Xinwang Liu 0002, Zhiping Cai   +7 more
openaire   +3 more sources

Topological identification and interpretation for single-cell gene regulation elucidation across multiple platforms using scMGCA

Nature Communications, 2023
A major challenge in analyzing scRNA-seq data arises from challenges related to dimensionality and the prevalence of dropout events. Here the authors develop a deep graph learning method called scMGCA based on a graph-embedding autoencoder that ...
Zhuohan Yu, Yanchi Su, Yifu Lu, Yuning Yang, Fuzhou Wang, Shixiong Zhang, Yi Chang, Ka-Chun Wong, Xiangtao Li   +8 more
doaj   +1 more source

Link Activation Using Variational Graph Autoencoders [PDF]

IEEE Communications Letters, 2021
An unsupervised method is proposed for link activation in wireless networks by identifying clusters of interfering users. A k-nearest neighbors interference graph is first defined for the wireless network which is then mapped to a stochastic latent space. The users are then clustered in the latent space using a Gaussian mixture model, and one user from
Saeed Jamshidiha, Vahid Pourahmadi, Abbas Mohammadi 0002, Mehdi Bennis   +3 more
openaire   +2 more sources

Deep Subspace Clustering Fused with Auto-Weight Learning [PDF]

Jisuanji gongcheng, 2022
Subspace clustering is a clustering method for high-dimensional data.This method offers a unique way of data self-representation and high clustering accuracy.The limitation of traditional subspace clustering is its focus on constructing the optimal ...
JIANG Yuyan, SHAO Jin, LI Ping
doaj   +1 more source

Autoencoder Architectures for Low-Rate Sparse Point Cloud Geometry Coding

IEEE Access
Efficient compression of sparse point cloud geometry remains a critical challenge in 3D content processing, particularly for low-rate scenarios where conventional codecs struggle to maintain efficiency. This work proposes a system-level framework for low-
Ivaylo Bozhilov, Radostina Petkova, Krasimir Tonchev, Agata Manolova, Vladimir Poulkov, H. Vincent Poor   +5 more
doaj   +1 more source

Stacked Denoising Extreme Learning Machine Autoencoder Based on Graph Embedding for Feature Representation

IEEE Access, 2019
Extreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification ...
Hongwei Ge, Weiting Sun, Mingde Zhao, Yao Yao   +3 more
doaj   +1 more source

Dynamic Joint Variational Graph Autoencoders [PDF]

, 2020
Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dynamic networks and evolve over time. Most existing graph embedding algorithms were developed for static graphs mainly and cannot capture
Sedigheh Mahdavi, Shima Khoshraftar, Aijun An   +2 more
openaire   +3 more sources

Graph-Structured Network Traffic Modelling for Anomaly-Based Intrusion Detection

Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI)
The increasing complexity of cyber threats demands more advanced network intrusion detection systems (NIDS) capable of identifying both known and emerging attack patterns.
Baskoro Adi Pratomo, Muhammad Farhan Haykal, Hudan Studiawan, Diana Purwitasari   +3 more
doaj   +1 more source

3D Conformational Generative Models for Biological Structures Using Graph Information-Embedded Relative Coordinates

Molecules, 2022
Developing molecular generative models for directly generating 3D conformation has recently become a hot research area. Here, an autoencoder based generative model was proposed for molecular conformation generation. A unique feature of our method is that
Mingyuan Xu, Weifeng Huang, Min Xu, Jinping Lei, Hongming Chen   +4 more
doaj   +1 more source

Graph Masked Autoencoder for Sequential Recommendation

Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023
While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from poor representation capability in label scarcity scenarios.
Yaowen Ye, Lianghao Xia, Chao Huang 0001
openaire   +4 more sources