English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Learning feature interactions is the key to success for the large-scale CTRprediction and recommendation. In practice, handcrafted feature engineeringusually requires exhaustive searching. In order to reduce the high cost ofhuman efforts in feature engineering, researchers propose several deep neuralnetworks (DNN)-based approaches to learn the feature interactions in anend-to-end fashion. However, existing methods either do not learn bothvector-wise interactions and bit-wise interactions simultaneously, or fail tocombine them in a controllable manner. In this paper, we propose a new model,xDeepInt, based on a novel network architecture called polynomial interactionnetwork (PIN) which learns higher-order vector-wise interactions recursively.By integrating subspace-crossing mechanism, we enable xDeepInt to balance themixture of vector-wise and bit-wise feature interactions at a bounded order.Based on the network architecture, we customize a combined optimizationstrategy to conduct feature selection and interaction selection. We implementthe proposed model and evaluate the model performance on three real-worlddatasets. Our experiment results demonstrate the efficacy and effectiveness ofxDeepInt over state-of-the-art models. We open-source the TensorFlowimplementation of xDeepInt: https://github.com/yanyachen/xDeepInt.

xDeepInt: a hybrid architecture for modeling the vector-wise and bit-wise feature interactions