Enhancing CTR Prediction with Context-Aware Feature Representation Learning

Abstract

CTR prediction has been widely used in the real world. Many methods model feature interaction to improve their performance. However, most methods only learn a fixed representation for each feature without considering the varying importance of each feature under different contexts, resulting in inferior performance. Recently, several methods tried to learn vector-level weights for feature representations to address the fixed representation issue. However, they only produce linear transformations to refine the fixed feature representations, which are still not flexible enough to capture the varying importance of each feature under different contexts. In this paper, we propose a novel module named Feature Refinement Network (FRNet), which learns context-aware feature representations at bit-level for each feature in different contexts. FRNet consists of two key components: 1) Information Extraction Unit (IEU), which captures contextual information and cross-feature relationships to guide context-aware feature refinement; and 2) Complementary Selection Gate (CSGate), which adaptively integrates the original and complementary feature representations learned in IEU with bit-level weights. Notably, FRNet is orthogonal to existing CTR methods and thus can be applied in many existing methods to boost their performance. Comprehensive experiments are conducted to verify the effectiveness, efficiency, and compatibility of FRNet.

arXiv commentSIGIR 2022

References in corpus (9)

• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
• FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
• Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
• Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
• An Embedding Learning Framework for Numerical Features in CTR Prediction
• Network On Network for Tabular Data Classification in Real-world Applications
• TFNet: Multi-Semantic Feature Interaction for CTR Prediction

Cited by in corpus (5)

• CL4CTR: A Contrastive Learning Framework for CTR Prediction
• Distribution-Guided Auto-Encoder for User Multimodal Interest Cross Fusion
• Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives
• Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders
• Dual-Stream MLP is All You Need for CTR Prediction