BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning
This benchmark addresses the need for accessible, standardized evaluation of hyperparameter optimization methods for unsupervised biological representation learning, a domain where such benchmarks were previously lacking.
The paper introduces BBOmix, the first open-source tabular benchmark for hyperparameter optimization of unsupervised representation learning on real-world biological data, comprising 105,000 evaluations across four autoencoder architectures and seven multi-omics modalities. It quantifies the correlation between reconstruction loss and downstream performance and establishes baselines for various HPO methods.
The rapid advancement of high-throughput sequencing has led to large, high-dimensional omics datasets. Deep unsupervised learning architectures, particularly Autoencoders (AEs), are increasingly used for dimensionality reduction and representation learning in this domain. However, AEs are highly sensitive to architectural choices and hyperparameters, and unsupervised optimization typically relies on reconstruction loss, which may be a poor proxy for downstream utility. Exhaustive hyperparameter optimization (HPO) is computationally expensive, leading researchers to frequently rely on suboptimal default configurations. To democratize access to large-scale unsupervised HPO research, we introduce $\textbf{BBOmix}$, the first open-source tabular benchmark for unsupervised representation learning on real-world biological data. Our benchmark includes 105,000 evaluations across four AE architectures and seven multi-omics modalities from the TCGA and SCHC datasets. We quantify the correlation between reconstruction loss and downstream task performance and provide an extensive evaluation of state-of-the-art single-fidelity, multi-fidelity, and transfer learning HPO methods, establishing a rigorous baseline for future research in unsupervised biological representation learning.