Bayesian integration provides principled posterior estimates for both aleatoric and epistemic uncertainty, but suffers from performance degradation on large knowledge graphs due to the computational weight of exact inference or variational surrogates.

Authors

• Person: Not available Organization: Springer
  A Comprehensive Review of Neuro-symbolic AI for Robustness ...

Sources

• A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer via serper

Referenced by nodes (1)

• knowledge graphs concept