EGC2: Enhanced graph classification with easy graph compression

Chen, Jinyin; Xiong, Haiyang; Zheng, Haibin; Zhang, Dunjie; Zhang, Jian; Jia, Mingwei; Liu, Yi

doi:10.1016/j.ins.2023.01.114

Cited by 11 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TemFin consists of half a month of transactions sampled from a private financial transfer transaction network in the Ant Finance Group. 3 Details of all datasets are described in Table 5 in the Appendix due to the page limitations. All datasets are sequentially split according to the edge timestamp order by 70%, 15%, and 15% for training, validation, and testing, respectively [44].…”

Section: Experiments 51 Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

et al. 2022

View full text Add to dashboard Cite

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle variabilities across subjects, channels and time points. Thus, capturing fine-grained, discriminative features of EEG patterns, which is associated with high-frequency textural information, is yet to be resolved. In this work, we propose Scattering Transformer (ScatterFormer), an invariant scattering transform-based hierarchical Transformer that specifically pays attention to subtle features. In particular, the disentangled frequency-aware attention (FAA) enables the Transformer to capture clinically informative high-frequency components, offering a novel clinical explainability based on visual encoding of multichannel EEG signals. Evaluations on two distinct tasks of epileptiform detection demonstrate the effectiveness our method. Our proposed model achieves median AUCROC and accuracy of 98.14%, 96.39% in patients with Rolandic epilepsy. On a neonatal seizure detection benchmark, it outperforms the state-of-the-art by 9% in terms of average AUCROC.

show abstract

Section: Experiments 51 Experimental Settingsmentioning

confidence: 99%

“…Temporal Graph Networks (TGNs) are designed to generate temporal node representations of TIGs by encoding the neighborhoods for the target node at any given timestamp [3,40,41,43]. They typically encode their neighborhoods based on a fixed, pre-defined rule.…”

Section: Introductionmentioning

confidence: 99%