Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Laika zināšanu grafu analīze× | Daudzslāņu zināšanu grafu analīze× | |
|---|---|---|
| Nozare | Tīklu analīze | Tīklu analīze |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2017–2018 | 2014–2016 |
| Autors≠ | Trivedi, R. et al.; Dasgupta, S. S. et al. | Kivela, M. et al.; Nickel, M. et al. |
| Tips≠ | Temporal graph embedding and reasoning | Graph-based analytical framework |
| Pirmavots≠ | Trivedi, R., Dai, H., Wang, Y., & Song, L. (2017). Know-Evolve: Deep temporal reasoning for dynamic knowledge graphs. Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 3462–3471. link ↗ | Kivela, M., Arenas, A., Barthelemy, M., Gleeson, J. P., Moreno, Y., & Porter, M. A. (2014). Multilayer networks. Journal of Complex Networks, 2(3), 203–271. DOI ↗ |
| Citi nosaukumi | TKG analysis, temporal KG analysis, dynamic knowledge graph analysis, time-aware knowledge graph analysis | multi-relational knowledge graph analysis, multilayer KG analysis, multi-relational graph analysis, multiplex knowledge graph analysis |
| Saistītās | 5 | 5 |
| Kopsavilkums≠ | Temporal Knowledge Graph Analysis extends standard knowledge graph methods to data where facts and relationships carry timestamps or validity intervals. It enables reasoning about how entities and relations evolve over time, supporting tasks such as link prediction for future facts, temporal relation classification, and event forecasting in dynamic relational data. | Multilayer knowledge graph analysis treats a knowledge base as a stack of relation-specific network layers sharing the same entity set, enabling simultaneous reasoning across relation types. Unlike a flat single-layer graph, it preserves the semantic distinctions between relation types and supports cross-layer link prediction, entity alignment, and community detection grounded in multilayer network theory. |
| ScholarGateDatu kopa ↗ |
|
|