On the Structural (Dis)Agreement of Landscape Representations in Black-Box Optimization
For researchers in meta-learning and algorithm selection for black-box optimization, this paper provides empirical evidence that landscape representations capture complementary aspects, highlighting the need for multi-view analyses.
This paper evaluates four landscape feature representations (ELA, DeepELA, TransOptAS, DoE2Vec) on MA-BBOB problems, finding they organize problems differently and no single representation dominates. They also show an inherent trade-off between structural landscape descriptions and algorithm performance across Differential Evolution and Particle Swarm Optimization.
Landscape feature representations play a central role in automated algorithm selection and meta-learning for black-box optimization, yet little is known about how different representations agree (or disagree) in the structures they impose on problem spaces. This paper presents a systematic unsupervised evaluation of four state-of-the-art representations (ELA, DeepELA, TransOptAS, and DoE2Vec) using a diverse set of affine combinations of BBOB functions (MA-BBOB). By applying extensive clustering analyses, coverage-based stability measures, and cross-representation similarity assessments, we show that each representation organizes the same problems in markedly different ways: ELA and TransOptAS form compact geometric structures, DeepELA provides a balanced intermediate view, and DoE2Vec achieves strong semantic alignment but with substantial fragmentation. Our results reveal that no single representation dominates; rather, they capture complementary aspects of the underlying landscapes. These findings highlight the importance of multi-view analyses for understanding representation behavior and offer guidance on selecting or combining representations in downstream meta-learning and algorithm selection tasks. In addition, across two different algorithm families (Differential Evolution and Particle Swarm Optimization), we show that landscape representations face an inherent trade-off in how well they align structural landscape descriptions with observed performance, indicating that no single representation can fully capture algorithm performance.