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 |