TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning

TL;DR

TransBO introduces a two-phase transfer learning framework for hyperparameter optimization that adaptively leverages past tasks to improve current HPO efficiency, demonstrating superior performance across various settings.

Contribution

It presents a novel two-phase transfer learning approach that jointly and adaptively aggregates knowledge from multiple source tasks for hyperparameter optimization.

Findings

TransBO outperforms existing methods in static and dynamic transfer learning settings.

It effectively handles the complementary nature of source tasks and knowledge aggregation.

Experimental results include neural architecture search, showing broad applicability.

Abstract

With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important. Motivated by the tuning behaviors of human experts, it is intuitive to leverage auxiliary knowledge from past HPO tasks to accelerate the current HPO task. In this paper, we propose TransBO, a novel two-phase transfer learning framework for HPO, which can deal with the complementary nature among source tasks and dynamics during knowledge aggregation issues simultaneously. This framework extracts and aggregates source and target knowledge jointly and adaptively, where the weights can be learned in a principled manner. The extensive experiments, including static and dynamic transfer learning settings and neural architecture search, demonstrate the superiority of TransBO over the state-of-the-arts.