Enum GnnAggregation 

pub enum GnnAggregation {
    Sum,
    Mean,
    Max,
}

Neighbour feature aggregation strategy used during message passing.

Note: named GnnAggregation (not AggregationMethod) to avoid collision with the same-named type already exported from the gradient module.

Variants

Sum

Weighted sum of neighbour features (weight from edge).

Mean

Weighted sum divided by total edge weight; falls back to own features if the node is isolated.

Max

Element-wise maximum across neighbours (unweighted); falls back to own features if the node is isolated.

Trait Implementations

impl Clone for GnnAggregation

fn clone(&self) -> GnnAggregation

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for GnnAggregation

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for GnnAggregation

fn eq(&self, other: &GnnAggregation) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for GnnAggregation