Research Article
Session Recommendation Model Based on Context-Aware and Gated Graph Neural Networks
Table 3
Comparison of the experimental results of CA-GGNN with TAGNN and DGTN (%).
| | Method | Yoochoose1/64 | Yoochoose1/4 | Diginetica | | P@20 | MRR@20 | P@20 | MRR@20 | P@20 | MRR@20 |
| | TAGNN | 70.17 | 30.46 | 71.05 | 30.96 | 50.02 | 17.18 | | DGTN | 70.21 | 31.08 | 71.38 | 31.37 | 50.35 | 17.33 | | CA-GGNN | 70.84 | 31.83 | 72.93 | 32.91 | 51.12 | 18.48 | | Improve | 0.63 | 0.75 | 1.55 | 1.18 | 0.77 | 1.15 |
|
|
Bold shows the experimental result of the model proposed in this paper.
|