Siamese Meta-Learning and Algorithm Selection with 'Algorithm-Performance Personas' [Proposal]
This work addresses the challenge of improving algorithm selection in meta-learning for researchers and practitioners, though it appears incremental as it builds on existing automated selection methods.
The paper tackles the problem of insufficient information from meta-features in automated per-instance algorithm selection by proposing a Siamese Neural Network architecture that focuses on 'alike performing' instances, introducing a novel performance metric and method for training sample selection, with initial evidence showing it outperforms standard metrics like absolute errors.
Automated per-instance algorithm selection often outperforms single learners. Key to algorithm selection via meta-learning is often the (meta) features, which sometimes though do not provide enough information to train a meta-learner effectively. We propose a Siamese Neural Network architecture for automated algorithm selection that focuses more on 'alike performing' instances than meta-features. Our work includes a novel performance metric and method for selecting training samples. We introduce further the concept of 'Algorithm Performance Personas' that describe instances for which the single algorithms perform alike. The concept of 'alike performing algorithms' as ground truth for selecting training samples is novel and provides a huge potential as we believe. In this proposal, we outline our ideas in detail and provide the first evidence that our proposed metric is better suitable for training sample selection that standard performance metrics such as absolute errors.