# ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning

arXiv: https://arxiv.org/abs/2503.09315 · HTML: https://mlsanity.com/paper/2503.09315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation](https://mlsanity.com/paper/1601.02828/) (2016)
- [Learning to Embed Categorical Features without Embedding Tables for Recommendation](https://mlsanity.com/paper/2010.10784/) (2020)
- [Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems](https://mlsanity.com/paper/2007.14523/) (2020)
- [AutoField: Automating Feature Selection in Deep Recommender Systems](https://mlsanity.com/paper/2204.09078/) (2022)
- [Post-Training 4-bit Quantization on Embedding Tables](https://mlsanity.com/paper/1911.02079/) (2019)
- [Deep Clustering based Fair Outlier Detection](https://mlsanity.com/paper/2106.05127/) (2021)
- [Mixed-Precision Embedding Using a Cache](https://mlsanity.com/paper/2010.11305/) (2020)
- [Single-shot Embedding Dimension Search in Recommender System](https://mlsanity.com/paper/2204.03281/) (2022)
- [Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction](https://mlsanity.com/paper/2212.05735/) (2022)
- [SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems](https://mlsanity.com/paper/2308.09395/) (2023)

## Abstract (arXiv)

Feature optimization -- specifically Feature Selection (FS) and Dimension Selection (DS) -- is critical for the efficiency and generalization of large-scale recommender systems. While conceptually related, these tasks are typically tackled with isolated solutions that often suffer from ambiguous importance scores or prohibitive computational costs. In this paper, we propose ShuffleGate, a unified and interpretable mechanism that estimates component importance by measuring the model's sensitivity to information loss. Unlike conventional gating that learns relative weights, ShuffleGate introduces a batch-wise shuffling strategy to effectively "erase" information in an end-to-end differentiable manner. This paradigm shift yields naturally polarized importance distributions, bridging the long-standing "search-retrain gap" and distinguishing essential signals from noise without complex threshold tuning. Extensive experiments across four benchmarks validate that ShuffleGate consistently outperforms state-of-the-art methods in both Feature and Dimension Selection tasks. It achieves a 15× speedup over permutation baselines and demonstrates extreme scalability by processing 270M parameters in just 700 seconds. Finally, in a top-tier industrial deployment, it compressed input dimensions by 10×, yielding a 91% increase in training throughput while serving billions of daily requests without performance degradation.