Enum CondensationMethod 

#[non_exhaustive]
pub enum CondensationMethod {
    KCenter,
    ImportanceSampling,
    GradientMatching,
    Herding,
}

Method used for graph condensation.

Each variant represents a different algorithmic approach to reducing a graph while preserving its structural properties.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

KCenter

Greedy farthest-point sampling (coreset). Picks nodes that maximize minimum distance to the selected set.

ImportanceSampling

Degree-weighted sampling with feature diversity. Combines structural importance (degree) with feature-space coverage.

GradientMatching

Gradient matching between original and synthetic graphs. Optimises a small synthetic graph so that GNN gradients match those computed on the full graph.

Herding

Kernel herding selection. Greedily picks points that minimize the Maximum Mean Discrepancy (MMD) between the selected subset and the full dataset.

Trait Implementations

impl Clone for CondensationMethod

fn clone(&self) -> CondensationMethod

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CondensationMethod

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

Formats the value using the given formatter.

impl PartialEq for CondensationMethod

fn eq(&self, other: &CondensationMethod) -> 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 Copy for CondensationMethod

impl Eq for CondensationMethod

impl StructuralPartialEq for CondensationMethod