# Optimizing Feature Set for Click-Through Rate Prediction

arXiv: https://arxiv.org/abs/2301.10909 · HTML: https://mlsanity.com/paper/2301.10909/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2023.

## Built on by (most cited first, 13 of 13)

- [Explicit Feature Interaction-aware Uplift Network for Online Marketing](https://mlsanity.com/paper/2306.00315/) (2023)
- [MvFS: Multi-view Feature Selection for Recommender System](https://mlsanity.com/paper/2309.02064/) (2023)
- [ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems](https://mlsanity.com/paper/2403.12660/) (2024)
- [ICE-SEARCH: A Language Model-Driven Feature Selection Approach](https://mlsanity.com/paper/2402.18609/) (2024)
- [OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction](https://mlsanity.com/paper/2408.08585/) (2024)
- [Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization](https://mlsanity.com/paper/2310.04693/) (2023)
- [Fusion Matters: Learning Fusion in Deep Click-through Rate Prediction Models](https://mlsanity.com/paper/2411.15731/) (2024)
- [Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network](https://mlsanity.com/paper/2310.15342/) (2023)
- [How Usable is Automated Feature Engineering for Tabular Data?](https://mlsanity.com/paper/2508.13932/) (2025)
- [From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs](https://mlsanity.com/paper/2502.13471/) (2025)
- [ICAFS: Inter-Client-Aware Feature Selection for Vertical Federated Learning](https://mlsanity.com/paper/2504.10851/) (2025)
- [IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval](https://mlsanity.com/paper/2504.17529/) (2025)
- [LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems](https://mlsanity.com/paper/2606.01111/) (2026)

## Abstract (arXiv)

Click-through prediction (CTR) models transform features into latent vectors and enumerate possible feature interactions to improve performance based on the input feature set. Therefore, when selecting an optimal feature set, we should consider the influence of both feature and its interaction. However, most previous works focus on either feature field selection or only select feature interaction based on the fixed feature set to produce the feature set. The former restricts search space to the feature field, which is too coarse to determine subtle features. They also do not filter useless feature interactions, leading to higher computation costs and degraded model performance. The latter identifies useful feature interaction from all available features, resulting in many redundant features in the feature set. In this paper, we propose a novel method named OptFS to address these problems. To unify the selection of feature and its interaction, we decompose the selection of each feature interaction into the selection of two correlated features. Such a decomposition makes the model end-to-end trainable given various feature interaction operations. By adopting feature-level search space, we set a learnable gate to determine whether each feature should be within the feature set. Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates. Hence, OptFS generates the feature set only containing features which improve the final prediction results. Experimentally, we evaluate OptFS on three public datasets, demonstrating OptFS can optimize feature sets which enhance the model performance and further reduce both the storage and computational cost.