TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation

Effective feature interaction modeling is critical for enhancing the accuracy of click-through rate (CTR) prediction in industrial recommender systems. Most of the current deep CTR models resort to building complex network architectures to better capture intricate feature interactions (FIs) or user behaviors. However, we identify two limitations in these models: 1) the samples given to the model are undifferentiated, which may lead the model to learn a larger number of easy samples in a single-minded manner while ignoring a smaller number of hard samples, thus reducing the model’s generalization ability; and 2) differentiated FI encoders are designed to capture different interactions information but receive consistent supervision signals, thereby limiting the effectiveness of the encoder. To bridge the identified gaps, this article introduces a novel CTR prediction framework by integrating the plug-and-playTwin Focus (TF) Loss,Sample Selection Embedding Module (SSEM), andDynamic Fusion Module (DFM), named the TF Framework for CTR (TF4CTR). Specifically, the framework employs the SSEM at the bottom of the model to differentiate between samples, thereby assigning a more suitable encoder for each sample. Meanwhile, the TF Loss provides tailored supervision signals to both simple and complex encoders. Moreover, the DFM dynamically fuses the FI information captured by the encoders, resulting in more accurate predictions. Experiments on five real-world datasets confirm the effectiveness and compatibility of the framework, demonstrating its capacity to enhance various representative baselines in a model-agnostic manner.