$L_0$ Regularization of Field-Aware Factorization Machine through Ising Model
This is an incremental improvement for machine learning practitioners using factorization machines, enhancing model interpretability and feature selection.
The paper tackled the problem of improving generalization in field-aware factorization machines by using the Ising model for L0 regularization, resulting in better performance and simultaneous determination of optimal feature combinations across groups.
We examined the use of the Ising model as an $L_0$ regularization method for field-aware factorization machines (FFM). This approach improves generalization performance and has the advantage of simultaneously determining the best feature combinations for each of several groups. We can deepen the interpretation and understanding of the model from the similarities and differences in the features selected in each group.