BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning

TL;DR

BOML is a Python library that unifies various meta-learning algorithms within a modular bilevel optimization framework, facilitating easier implementation and experimentation.

Contribution

It introduces a modular, hierarchical optimization library that consolidates multiple meta-learning methods into a common bilevel framework.

Findings

Supports meta-feature and meta-initialization methods

Provides flexible, reusable optimization modules

Enables streamlined meta-learning research and development

Abstract

Meta-learning (a.k.a. learning to learn) has recently emerged as a promising paradigm for a variety of applications. There are now many meta-learning methods, each focusing on different modeling aspects of base and meta learners, but all can be (re)formulated as specific bilevel optimization problems. This work presents BOML, a modularized optimization library that unifies several meta-learning algorithms into a common bilevel optimization framework. It provides a hierarchical optimization pipeline together with a variety of iteration modules, which can be used to solve the mainstream categories of meta-learning methods, such as meta-feature-based and meta-initialization-based formulations. The library is written in Python and is available at https://github.com/dut-media-lab/BOML.