HpLapGCN: Hypergraph p-Laplacian graph convolutional networks

2019 ◽  
Vol 362 ◽  
pp. 166-174 ◽  
Author(s):  
Sichao Fu ◽  
Weifeng Liu ◽  
Yicong Zhou ◽  
Liqiang Nie
Keyword(s):  
Convolutional Networks ◽  
Laplacian Graph

scholarly journals Multilabel Classification Based on Graph Neural Networks

2021 ◽  
Author(s):  
Wei-Cheng Ye ◽  
Jia-Ching Wang
Keyword(s):  
Neural Networks ◽  
Gaussian Noise ◽  
Input Data ◽  
Multilabel Classification ◽  
Laplacian Matrices ◽  
Convolutional Networks ◽  
Multilabel Learning ◽  
Laplacian Graph ◽  
Open Datasets ◽  
Graph Neural Networks

Typical Laplacian embedding focuses on building Laplacian matrices prior to minimizing weights of connected graph components. However, for multilabel problems, it is difficult to determine such Laplacian graphs owing to multiple relations between vertices. Unlike typical approaches that require precomputed Laplacian matrices, this chapter presents a new method for automatically constructing Laplacian graphs during Laplacian embedding. By using trace minimization techniques, the topology of the Laplacian graph can be learned from input data, subsequently creating robust Laplacian embedding and influencing graph convolutional networks. Experiments on different open datasets with clean data and Gaussian noise were carried out. The noise level ranged from 6% to 12% of the maximum value of each dataset. Eleven different multilabel classification algorithms were used as the baselines for comparison. To verify the performance, three evaluation metrics specific to multilabel learning are proposed because multilabel learning is much more complicated than traditional single-label settings; each sample can be associated with multiple labels. The experimental results show that the proposed method performed better than the baselines, even when the data were contaminated by noise. The findings indicate that the proposed method is reliably robust against noise.

scholarly journals Label-Aware Graph Convolutional Networks

2020 ◽  
Author(s):  
Hao Chen ◽  
Yue Xu ◽  
Feiran Huang ◽  
Zengde Deng ◽  
Wenbing Huang ◽  
...  
Keyword(s):  
Convolutional Networks

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

Sign in / Sign up

Export Citation Format

Share Document