Machine learningDeep learning / NLP / CV

Polu-nadgledana grafička neuronska mreža

Polu-nadgledana grafička neuronska mreža (GNN) trenira se na grafu gdje samo mali dio čvorova nosi oznake, koristeći prolaz poruka susjedstva za širenje informacija iz označenih čvorova na neoznačene. Pristup, populariziran od strane Kipfa i Wellinga 2017. godine u radu o grafičkim konvolucijskim mrežama, postiže snažnu točnost klasifikacije čvorova čak i kada su označeni primjeri oskudni.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Izvori

  1. Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR 2017). link
  2. Zhou, D., Bousquet, O., Lal, T. N., Weston, J., & Scholkopf, B. (2004). Learning with Local and Global Consistency. Advances in Neural Information Processing Systems (NeurIPS 2004), 17. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Semi-supervised Graph Neural Network (GNN with Label Propagation). ScholarGate. https://scholargate.app/hr/deep-learning/semi-supervised-graph-neural-network

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateSemi-supervised Graph Neural Network (Semi-supervised Graph Neural Network (GNN with Label Propagation)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/semi-supervised-graph-neural-network · Skup podataka: https://doi.org/10.5281/zenodo.20539026