Click-through rate (CTR) prediction is a cornerstone of modern recommender systems and online advertising platforms. Parallel CTR models utilize multiple sub-networks to capture diverse feature interactions and achieve advanced performance. However, these models face two key limitations: (1) reliance on shared, static feature embeddings limits their ability to capture distinct interaction signals across parallel sub-networks; and (2) although effective for modeling high-order interactions, the conventional layer-by-layer interaction paradigm propagates and amplifies noise cumulatively, thereby reducing model robustness. To address these challenges, we propose Decoupled Gated Network (DGNet), a novel framework that introduces two key components: Decoupled Embedding Generator (DEG) adaptively generates sub-network-specific embeddings from original representations, enhancing interaction specificity. Gated Fusion Module (GateF) dynamically extracts layer-wise complementary information from decoupled embeddings to mitigate cumulative interaction noise. DGNet and its two components are model-agnostic and can be seamlessly integrated into existing parallel CTR models. Extensive experiments show that DGNet consistently improves the performance of various parallel CTR models, yielding statistically significant performance boosting. Meanwhile, visualization and quantitative analyses provide an intuitively explanation for its reliability and performance improvements.

Click Through Rate (CTR) prediction plays an essential role in recommender systems and online advertising.It is crucial to effectively model feature interactions to improve the prediction performance of CTR models.However, existing methods face three significant challenges.First, while most methods can automatically capture high-order feature interactions, their performance tends to diminish as the order of feature interactions increases.Second, existing methods lack the ability to provide convincing interpretations of the prediction results, especially for high-order feature interactions, which limits the trustworthiness of their predictions.Third, many methods suffer from the presence of redundant parameters, particularly in the embedding layer.This paper proposes a novel method called Gated Deep Cross Network (GDCN) and a Field-level Dimension Optimization (FDO) approach to address these challenges.As the core structure of GDCN, Gated Cross Network (GCN) captures explicit high-order feature interactions and dynamically filters important interactions with an information gate in each order.Additionally, we use the FDO approach to learn condensed dimensions for each field based on their importance.Comprehensive experiments on five datasets demonstrate the effectiveness, superiority and interpretability of GDCN.Moreover, we verify the effectiveness of FDO in learning various dimensions and reducing model parameters.The code is available on https://github.com/anonctr/GDCN.

Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for each feature, which results in sub-optimal feature representations and thus inferior CTR prediction performance. For instance, low frequency features, which account for the majority of features in many CTR tasks, are less considered in standard supervised learning settings, leading to sub-optimal feature representations. In this paper, we introduce self-supervised learning to produce high-quality feature representations directly and propose a model-agnostic Contrastive Learning for CTR (CL4CTR) framework consisting of three self-supervised learning signals to regularize the feature representation learning: contrastive loss, feature alignment, and field uniformity. The contrastive module first constructs positive feature pairs by data augmentation and then minimizes the distance between the representations of each positive feature pair by the contrastive loss. The feature alignment constraint forces the representations of features from the same field to be close, and the field uniformity constraint forces the representations of features from different fields to be distant. Extensive experiments verify that CL4CTR achieves the best performance on four datasets and has excellent effectiveness and compatibility with various representative baselines.

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.