Table 4 Contribution of different components of our proposed method
From: Information cascades prediction with attention neural network
| MSE (t = 1*) | MSE (t = 2*) | MSE (t = 3*) | |
|---|---|---|---|
| Proposed (no \(\varvec{gate}\)) | 2.956 | 2.811 | 2.513 |
| Proposed (no \(\varvec{attention}\)) | 3.226 | 3.124 | 2.825 |
| Proposed (no\(\varvec{attention+gate}\)) | 3.726 | 3.419 | 3.376 |
| Proposed | 2.609 | 2.349 | 2.300 |
| AMiner | |||
| Proposed (no \(\varvec{gate}\)) | 2.285 | 1.706 | 1.592 |
| Proposed (no \(\varvec{attention}\)) | 2.339 | 1.816 | 1.763 |
| Proposed (no \(\varvec{attention+gate}\)) | 2.462 | 1.928 | 1.809 |
| Proposed | 2.172 | 1.672 | 1.534 |