Predicting Software Performance with Divide-and-Learn

In this paper, we propose an approach based on the concept of ‘divide-and-learn’, dubbed DaL. The basic idea is that, to handle sample sparsity, we divide the samples from the configuration landscape into distant divisions, for each of which we build a regularized Deep Neural Network as the local model to deal with the feature sparsity. A newly given configuration would then be assigned to the right model of division for the final prediction. Experiments on eight subject systems and five sample sizes have shown that DaL is state-of-the-art in 33 out of 40 cases.

The source codes, datasets, raw results, and supplementary materials can be found at our github repository.

The full paper can be downloaded here.