CR-BLEA: Contrastive Ranking for Adaptive Resource Allocation in Bilevel Evolutionary Algorithms

TL;DR

This paper introduces a contrastive ranking framework that adaptively allocates resources in bilevel evolutionary algorithms, significantly reducing computational costs while maintaining or improving solution quality.

Contribution

It proposes a novel contrastive ranking network and resource allocation strategy that selectively focuses on promising lower-level tasks in bilevel EAs, enhancing efficiency.

Findings

Reduces computational cost across five bilevel algorithms.

Maintains or improves solution accuracy with resource savings.

Demonstrates generalizability to various bilevel optimization scenarios.

Abstract

Bilevel optimization poses a significant computational challenge due to its nested structure, where each upper-level candidate solution requires solving a corresponding lower-level problem. While evolutionary algorithms (EAs) are effective at navigating such complex landscapes, their high resource demands remain a key bottleneck -- particularly the redundant evaluation of numerous unpromising lower-level tasks. Despite recent advances in multitasking and transfer learning, resource waste persists. To address this issue, we propose a novel resource allocation framework for bilevel EAs that selectively identifies and focuses on promising lower-level tasks. Central to our approach is a contrastive ranking network that learns relational patterns between paired upper- and lower-level solutions online. This knowledge guides a reference-based ranking strategy that prioritizes tasks for optimization and adaptively controls resampling based on estimated population quality. Comprehensive experiments across five state-of-the-art bilevel algorithms show that our framework significantly reduces computational cost while preserving -- or even enhancing -- solution accuracy. This work offers a generalizable strategy to improve the efficiency of bilevel EAs, paving the way for more scalable bilevel optimization.