Long Range Graph Benchmark

Dwivedi, Vijay Prakash; Rampášek, Ladislav; Galkin, Mikhail; Parviz, Ali; Wolf, Guy; Luu, Anh Tuan; Beaini, Dominique

doi:10.48550/arxiv.2206.08164

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model attains the highest mean performance for four out of the five datasets, with statistically significant improvements. (Dwivedi et al 2022). Shown is the mean ± s.d.…”

Section: Resultsmentioning

confidence: 99%

“…Description of Datasets Table 7 presents a summary of the statistics and characteristics of the datasets. The initial five datasets are sourced from (Dwivedi et al 2023), followed by two from (Dwivedi et al 2022), and finally the remaining datasets are obtained from (Kipf and Welling 2017;Chien et al 2020;Pei et al 2019). For more comprehensive details of the datasets, readers are encouraged to refer to (Rampášek et al 2022) and (Zhang et al 2022) (Dwivedi et al 2022).…”

Section: Discussionmentioning

confidence: 99%

“…We benchmark our method on five datasets in terms of graph classification and regression: ZINC, MNIST, CI-FAR10, PATTERN, and CLUSTER. • Long-Range Graph Benchmark (Dwivedi et al 2022).…”

Section: Experiments Settingmentioning

confidence: 99%

“…Computing Environment Our implementation is based on PyG (Fey and Lenssen 2019) (Dwivedi et al 2023(Dwivedi et al , 2022Kipf and Welling 2017;Chien et al 2020;Pei et al 2019).…”

Section: B Experimental Detailsmentioning

confidence: 99%

See 3 more Smart Citations

Dual-channel graph contrastive learning for self-supervised graph-level representation learning

Luo

Dong

Zheng

et al. 2023

Pattern Recognition

View full text Add to dashboard Cite

“…Our model attains the highest mean performance for four out of the five datasets, with statistically significant improvements. (Dwivedi et al 2022). Shown is the mean ± s.d.…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…We benchmark our method on five datasets in terms of graph classification and regression: ZINC, MNIST, CI-FAR10, PATTERN, and CLUSTER. • Long-Range Graph Benchmark (Dwivedi et al 2022).…”

Section: Experiments Settingmentioning

confidence: 99%

“…Computing Environment Our implementation is based on PyG (Fey and Lenssen 2019) (Dwivedi et al 2023(Dwivedi et al , 2022Kipf and Welling 2017;Chien et al 2020;Pei et al 2019).…”

Section: B Experimental Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Dual-channel graph contrastive learning for self-supervised graph-level representation learning

Luo

Dong

Zheng

et al. 2023

Pattern Recognition

View full text Add to dashboard Cite

“…On the one hand, when building topological graphs, every single frame image requires separate superpixel segmentation and topological graph building; then, all of the topological graphs will be connected selectively and merged together. On the other hand, the self-attention mechanism will be added to the GCN to enhance its ability to capture long-range interactions (LRI) [68] in graphs and learn the changes in structural features. In addition, we believe that it is possible to identify the motion status of the space target by the changes in structural features.…”

Section: Rapid Changes In Imaging Conditionsmentioning

confidence: 99%

Space Target Material Identification Based on Graph Convolutional Neural Network

Gong

Zhao

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Under complex illumination conditions, the spectral data distributions of a given material appear inconsistent in the hyperspectral images of the space target, making it difficult to achieve accurate material identification using only spectral features and local spatial features. Aiming at this problem, a material identification method based on an improved graph convolutional neural network is proposed. Superpixel segmentation is conducted on the hyperspectral images to build the multiscale joint topological graph of the space target global structure. Based on this, topological graphs containing the global spatial features and spectral features of each pixel are generated, and the pixel neighborhoods containing the local spatial features and spectral features are collected to form material identification datasets that include both of these. Then, the graph convolutional neural network (GCN) and the three-dimensional convolutional neural network (3-D CNN) are combined into one model using strategies of addition, element-wise multiplication, or concatenation, and the model is trained by the datasets to fuse and learn the three features. For the simulated data and the measured data, the overall accuracy of the proposed method can be kept at 85–90%, and their kappa coefficients remain around 0.8. This proves that the proposed method can improve the material identification performance under complex illumination conditions with high accuracy and strong robustness.

show abstract

Long Range Graph Benchmark

Cited by 2 publications

References 0 publications

Dual-channel graph contrastive learning for self-supervised graph-level representation learning

Dual-channel graph contrastive learning for self-supervised graph-level representation learning

Space Target Material Identification Based on Graph Convolutional Neural Network

Contact Info

Product

Resources

About