Table 1 Model performance under temporal split setting. Performance metrics are reported as mean (s.d.)
Model | CS@GT (↑) | CS@5 (↑) | CS@10 (↑) | CS@20 (↑) |
|---|---|---|---|---|
Ground Truth | 0.14 (—) | 0.30 (—) | 0.21 (—) | 0.16 (—) |
Random | 0.05 (0.12) | 0.01 (0.18) | 0.07 (0.23) | −0.05 (0.30) |
Popular | 0.18 (—) | 0.17 (—) | 0.24 (—) | 0.12 (—) |
LightGCN | 0.30 (0.04) | 0.27 (0.05) | 0.25 (0.03) | 0.26 (0.04) |
ConvNCF | 0.33 (0.03) | 0.34 (0.02) | 0.35 (0.02) | 0.35 (0.04) |
NCL | 0.37 (0.05) | 0.38 (0.05) | 0.37 (0.04) | 0.37 (0.03) |
Doc2Vec | 0.30 (0.02) | 0.32 (0.02) | 0.32 (0.03) | 0.33 (0.03) |
FRAMM | 0.35 (0.03) | 0.37 (0.03) | 0.37 (0.02) | 0.36 (0.04) |
DocTr-semantic | 0.42 (0.04) | 0.43 (0.04) | 0.43 (0.03) | 0.43 (0.03) |
DocTr-structural | 0.36 (0.03) | 0.37 (0.02) | 0.36 (0.04) | 0.35 (0.04) |
DocTr | 0.60 (0.02)* | 0.60 (0.02)* | 0.60 (0.04)* | 0.60 (0.03)* |
