Struct LearningRateScheduler 

pub struct LearningRateScheduler { /* private fields */ }

Learning rate scheduler for GNN training

Implements various scheduling strategies to control learning rate during training, helping prevent catastrophic forgetting and improve convergence.

Implementations

impl LearningRateScheduler

pub fn new(scheduler_type: SchedulerType, base_lr: f32) -> Self

Creates a new learning rate scheduler

Arguments

• scheduler_type - The scheduling strategy to use
• base_lr - The initial/base learning rate

Example

use ruvector_gnn::scheduler::{LearningRateScheduler, SchedulerType};

let scheduler = LearningRateScheduler::new(
    SchedulerType::StepDecay { step_size: 10, gamma: 0.9 },
    0.001
);

pub fn step(&mut self) -> f32

Advances the scheduler by one step and returns the new learning rate

For most schedulers, this should be called once per epoch. For ReduceOnPlateau, use step_with_metric instead.

Returns

The updated learning rate

pub fn step_with_metric(&mut self, metric: f32) -> f32

Advances the scheduler with a metric value (for ReduceOnPlateau)

Arguments

• metric - The metric value to monitor (e.g., validation loss)

Returns

The updated learning rate

pub fn get_lr(&self) -> f32

Gets the current learning rate without advancing the scheduler

pub fn reset(&mut self)

Resets the scheduler to its initial state

Trait Implementations

impl Clone for LearningRateScheduler

fn clone(&self) -> LearningRateScheduler

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LearningRateScheduler

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

Formats the value using the given formatter.