TAGNN++
Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Knowledge Base4 results
- HR@20· 2021-07-04SOTA71.91best: 72.62 (SR-PredAO+SGNNHN)
- MRR@20· 2021-07-0431.57best: 32.61 (SGNN-HN)
- Hit@20· 2021-07-0451.86best: 57.86 (SR-PredAO+DIDN)
- MRR@20· 2021-07-0417.93best: 20.49 (SR-PredAO+DIDN)