Feature-weighted elastic net: using "features of features" for better prediction
This is an incremental improvement for practitioners in fields like medical prediction, offering better feature selection and prediction accuracy when extra feature metadata is available.
The paper tackles the problem of improving prediction in supervised learning by leveraging additional information on features, proposing a feature-weighted elastic net method that outperforms the lasso in simulations and a preeclampsia prediction case, achieving a cross-validated AUC of 0.86 vs. 0.80.
In some supervised learning settings, the practitioner might have additional information on the features used for prediction. We propose a new method which leverages this additional information for better prediction. The method, which we call the feature-weighted elastic net ("fwelnet"), uses these "features of features" to adapt the relative penalties on the feature coefficients in the elastic net penalty. In our simulations, fwelnet outperforms the lasso in terms of test mean squared error and usually gives an improvement in true positive rate or false positive rate for feature selection. We also apply this method to early prediction of preeclampsia, where fwelnet outperforms the lasso in terms of 10-fold cross-validated area under the curve (0.86 vs. 0.80). We also provide a connection between fwelnet and the group lasso and suggest how fwelnet might be used for multi-task learning.