Module layer 

GNN Layer Implementation for HNSW Topology

This module implements graph neural network layers that operate on HNSW graph structure, including attention mechanisms, normalization, and gated recurrent updates.

Structs

GRUCell

Gated Recurrent Unit (GRU) cell for state updates

LayerNorm

Layer normalization

Linear

Linear transformation layer (weight matrix multiplication)

MultiHeadAttention

Multi-head attention mechanism

RuvectorLayer

Main GNN layer operating on HNSW topology