Report
Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
| العنوان: | Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network |
|---|---|
| المؤلفون: | Lyu, Fuyuan, Tang, Xing, Liu, Dugang, Ma, Chen, Luo, Weihong, Chen, Liang, He, Xiuqiang, Liu, Xue |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Information Retrieval |
| الوصف: | Deep sparse networks are widely investigated as a neural network architecture for prediction tasks with high-dimensional sparse features, with which feature interaction selection is a critical component. While previous methods primarily focus on how to search feature interaction in a coarse-grained space, less attention has been given to a finer granularity. In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks. To explore such expansive space, we propose a decomposed space which is calculated on the fly. We then develop a selection algorithm called OptFeature, which efficiently selects the feature interaction from both the feature field and the feature value simultaneously. Results from experiments on three large real-world benchmark datasets demonstrate that OptFeature performs well in terms of accuracy and efficiency. Additional studies support the feasibility of our method. Comment: NeurIPS 2023 poster |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2310.15342 |
| رقم الانضمام: | edsarx.2310.15342 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |