Transfer Learning for Algorithm Recommendation

by   Gean Trindade Pereira, et al.

Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorithms for several datasets can be used to learn which algorithm, from a set of options, would be more suitable for a new dataset [2]. Perhaps the most popular form of meta-learning is transfer learning, which consists of transferring knowledge acquired by a machine learning algorithm in a previous learning task to increase its performance faster in another and similar task [3]. Transfer Learning has been widely applied in a variety of complex tasks such as image classification, machine translation and, speech recognition, achieving remarkable results [4,5,6,7,8]. Although transfer learning is very used in traditional or base-learning, it is still unknown if it is useful in a meta-learning setup. For that purpose, in this paper, we investigate the effects of transferring knowledge in the meta-level instead of base-level. Thus, we train a neural network on meta-datasets related to algorithm recommendation, and then using transfer learning, we reuse the knowledge learned by the neural network in other similar datasets from the same domain, to verify how transferable is the acquired meta-knowledge.


page 1

page 2

page 3


FIND:Explainable Framework for Meta-learning

Meta-learning is used to efficiently enable the automatic selection of m...

Transferring Knowledge across Learning Processes

In complex transfer learning scenarios new tasks might not be tightly li...

An Easy to Use Repository for Comparing and Improving Machine Learning Algorithm Usage

The results from most machine learning experiments are used for a specif...

A Meta-Learning Approach to Population-Based Modelling of Structures

A major problem of machine-learning approaches in structural dynamics is...

Learning Heterogeneous Similarity Measures for Hybrid-Recommendations in Meta-Mining

The notion of meta-mining has appeared recently and extends the traditio...

Can a powerful neural network be a teacher for a weaker neural network?

The transfer learning technique is widely used to learning in one contex...

Hidden Incentives for Auto-Induced Distributional Shift

Decisions made by machine learning systems have increasing influence on ...

Please sign up or login with your details

Forgot password? Click here to reset