Name
Abstract | ||
|---|---|---|
The target of machine learning is a predictive model that performs well on unseen data. Often, such a model has multiple intended uses, related to different points in the tradeoff between (e.g.) sensitivity and specificity. Moreover, when feature selection is required, different feature subsets will suit different target performance characteristics. Given a feature selection task with such multiple distinct requirements, one is in fact faced with a very-many-objective optimization task, whose target is a Pareto surface of feature subsets, each specialized for (e.g.) a different sensitivity/specificity tradeoff profile. We argue that this view has many advantages. We motivate, develop and test such an approach. We show that it can be achieved successfully using a dominance-based multiobjective algorithm, despite an arbitrarily large number of objectives. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1007/978-3-642-15844-5_39 | PPSN (1) |
Keywords | Field | DocType |
feature selection,predictive model,multiple distinct requirement,feature subsets,different point,different feature subsets,different sensitivity,feature selection task,multi-purpose predictive model,multiple intended use,different target performance characteristic,many-objective task,machine learning,prediction model | Data mining,Dominance relation,Feature selection,Computer science,Feature (computer vision),Artificial intelligence,Machine learning,Arbitrarily large,Pareto principle | Conference |
Volume | ISSN | ISBN |
6238 | 0302-9743 | 3-642-15843-9 |
Citations | PageRank | References |
2 | 0.36 | 7 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alan P. Reynolds | 1 | 157 | 11.57 |
| David W. Corne | 2 | 2161 | 152.00 |
| Michael J. Chantler | 3 | 12 | 1.31 |