TayFCS: Towards Light Feature Combination Selection for Deep Recommender Systems

• URL: http://arxiv.org/abs/2507.03895v1
• Date: Sat, 05 Jul 2025 04:22:42 GMT
• Title: TayFCS: Towards Light Feature Combination Selection for Deep Recommender Systems
• Authors: Xianquan Wang, Zhaocheng Du, Jieming Zhu, Chuhan Wu, Qinglin Jia, Zhenhua Dong,
• Abstract summary: Taylor Expansion Scorer (TayScorer) module for field-wise Taylor expansion on the base model.<n> Logistic Regression Elimination (LRE) estimates the corresponding information gain based on the model prediction performance.
• Score: 44.80081613834248
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Feature interaction modeling is crucial for deep recommendation models. A common and effective approach is to construct explicit feature combinations to enhance model performance. However, in practice, only a small fraction of these combinations are truly informative. Thus it is essential to select useful feature combinations to reduce noise and manage memory consumption. While feature selection methods have been extensively studied, they are typically limited to selecting individual features. Extending these methods for high-order feature combination selection presents a significant challenge due to the exponential growth in time complexity when evaluating feature combinations one by one. In this paper, we propose $\textbf{TayFCS}$, a lightweight feature combination selection method that significantly improves model performance. Specifically, we propose the Taylor Expansion Scorer (TayScorer) module for field-wise Taylor expansion on the base model. Instead of evaluating all potential feature combinations' importance by repeatedly running experiments with feature adding and removal, this scorer only needs to approximate the importance based on their sub-components' gradients. This can be simply computed with one backward pass based on a trained recommendation model. To further reduce information redundancy among feature combinations and their sub-components, we introduce Logistic Regression Elimination (LRE), which estimates the corresponding information gain based on the model prediction performance. Experimental results on three benchmark datasets validate both the effectiveness and efficiency of our approach. Furthermore, online A/B test results demonstrate its practical applicability and commercial value.

Related papers

• NAN: A Training-Free Solution to Coefficient Estimation in Model Merging [61.36020737229637]
  We show that the optimal merging weights should scale with the amount of task-specific information encoded in each model.<n>We propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm.<n>NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies.
  arXiv  Detail & Related papers  (2025-05-22T02:46:08Z)
• Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection [52.716143424856185]
  We propose LiMA (Less input is More faithful for Attribution), which reformulates the attribution of important regions as an optimization problem for submodular subset selection.<n>LiMA identifies both the most and least important samples while ensuring an optimal attribution boundary that minimizes errors.<n>Our method also outperforms the greedy search in attribution efficiency, being 1.6 times faster.
  arXiv  Detail & Related papers  (2025-04-01T06:58:15Z)
• ShuffleGate: An Efficient and Self-Polarizing Feature Selection Method for Large-Scale Deep Models in Industry [12.690406065558394]
  ShuffleGate shuffles all feature values across instances simultaneously.<n>It can generate well-separated feature importance scores and estimate the performance without retraining the model.<n>It has been successfully integrated into the daily iteration of Bilibili's search models across various scenarios.
  arXiv  Detail & Related papers  (2025-03-12T12:05:03Z)
• Automated Model Selection for Tabular Data [0.1797555376258229]
  R's mixed effect linear models library allows users to provide interactive feature combinations in the model design. We aim to automate the model selection process for predictions on datasets incorporating feature interactions. The framework includes two distinct approaches for feature selection: a Priority-based Random Grid Search and a Greedy Search method.
  arXiv  Detail & Related papers  (2024-01-01T21:41:20Z)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning [68.12870241637636]
  We propose MILO, a model-agnostic subset selection framework that decouples the subset selection from model training. Our empirical results indicate that MILO can train models $3times - 10 times$ faster and tune hyperparameters $20times - 75 times$ faster than full-dataset training or tuning without performance.
  arXiv  Detail & Related papers  (2023-01-30T20:59:30Z)
• Learning to Maximize Mutual Information for Dynamic Feature Selection [13.821253491768168]
  We consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on the presently available information. We explore a simpler approach of greedily selecting features based on their conditional mutual information. The proposed method is shown to recover the greedy policy when trained to optimality, and it outperforms numerous existing feature selection methods in our experiments.
  arXiv  Detail & Related papers  (2023-01-02T08:31:56Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Compactness Score: A Fast Filter Method for Unsupervised Feature Selection [66.84571085643928]
  We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features. Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
  arXiv  Detail & Related papers  (2022-01-31T13:01:37Z)
• Memorize, Factorize, or be Na\"ive: Learning Optimal Feature Interaction Methods for CTR Prediction [29.343267933348372]
  We propose a framework called OptInter which finds the most suitable modelling method for each feature interaction. Our experiments show that OptInter improves the best performed state-of-the-art baseline deep CTR models by up to 2.21%.
  arXiv  Detail & Related papers  (2021-08-03T03:03:34Z)
• A hybrid ensemble method with negative correlation learning for regression [2.8484009470171943]
  This study automatically selects and weights sub-models from a heterogeneous model pool. It solves an optimization problem using an interior-point filtering linear-search algorithm. The value of this study lies in its ease of use and effectiveness, allowing the hybrid ensemble to embrace diversity and accuracy.
  arXiv  Detail & Related papers  (2021-04-06T06:45:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.