# Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction

arXiv: https://arxiv.org/abs/2311.04635 · HTML: https://mlsanity.com/paper/2311.04635/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2023.

## Built on by (most cited first, 20 of 20)

- [The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit](https://mlsanity.com/paper/2501.02173/) (2025)
- [GPRec: Bi-level User Modeling for Deep Recommenders](https://mlsanity.com/paper/2410.20730/) (2024)
- [Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation](https://mlsanity.com/paper/2503.05493/) (2025)
- [On the Practice of Deep Hierarchical Ensemble Network for Ad Conversion Rate Prediction](https://mlsanity.com/paper/2504.08169/) (2025)
- [Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction](https://mlsanity.com/paper/2505.17999/) (2025)
- [Contrastive Learning for Implicit Social Factors in Social Media Popularity Prediction](https://mlsanity.com/paper/2410.09345/) (2024)
- [TayFCS: Towards Light Feature Combination Selection for Deep Recommender Systems](https://mlsanity.com/paper/2507.03895/) (2025)
- [DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion](https://mlsanity.com/paper/2508.14500/) (2025)
- [Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions](https://mlsanity.com/paper/2512.00004/) (2025)
- [Unified Low-rank Compression Framework for Click-through Rate Prediction](https://mlsanity.com/paper/2405.18146/) (2024)
- [DTN: Deep Multiple Task-specific Feature Interactions Network for Multi-Task Recommendation](https://mlsanity.com/paper/2408.11611/) (2024)
- [From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs](https://mlsanity.com/paper/2502.13471/) (2025)
- [MATT-CTR: Unleashing a Model-Agnostic Test-Time Paradigm for CTR Prediction with Confidence-Guided Inference Paths](https://mlsanity.com/paper/2510.08932/) (2025)
- [Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives](https://mlsanity.com/paper/2512.01179/) (2025)
- [Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features](https://mlsanity.com/paper/2603.12586/) (2026)
- [Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate Prediction](https://mlsanity.com/paper/2605.24986/) (2026)
- [Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems](https://mlsanity.com/paper/2605.27450/) (2026)
- [SpecFormer: Mitigating Embedding and Attention Collapse via Spectral-Aware Transformer for Recommendation](https://mlsanity.com/paper/2607.24025/) (2026)
- [Building a User Foundation Model for the Open Web](https://mlsanity.com/paper/2607.28019/) (2026)
- [PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert](https://mlsanity.com/paper/2608.30449/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/anonctr/GDCN.