The forward propagation of R-GCN is calculated as: h_k^(l+1) = sigma(sum_{r in R} sum_{j in N_k^r} (1/c_{k,r}) W_r^(l) h_j^(l) + W_0^(l) h_k^(l)), where h_k^(l+1) is the hidden state of entity k in the l-th layer, N_k^r denotes a neighbor collection of entity k and relation r, c_{k,r} is the normalization process, and W_r and W_0 are weight matrices.

Authors

• Person: Not available Organization: Springer
  Knowledge Graphs: Opportunities and Challenges - Springer Nature

Sources

• Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Springer via serper

Referenced by nodes (1)

• entity concept