用布隆过滤器编码数据，省内存还隐藏原始特征值。
Bloom Filter Encoding for Machine Learning
- 用哈希将数据转为固定长度的位数组，无需密钥也可用
- 在6个数据集上表现接近原始数据，内存显著降低
- 适合需要隐私保护或高效存储的机器学习场景
我们提出一种基于布隆过滤器的机器学习数据预处理方法。每个样本通过基于哈希的编码转换为紧凑的位数组表示，生成固定长度特征空间，降低内存占用并隐藏原始特征值。该编码不依赖密钥哈希，但可选使用密钥控制映射，复现时需密钥。我们在六个跨文本、时间序列、表格和图像领域的数据集上评估：SMS Spam Collection、ECG200、Adult 50K、CDC Diabetes、MNIST 和 Fashion MNIST。采用四种分类器：极端梯度提升（XGBoost）、深度神经网络（DNN）、卷积神经网络（CNN）和逻辑回归。结果表明，使用布隆过滤器编码训练的模型，在多个数据集上性能与原始数据或标准降维方法相当，同时保持一致的内存节省。这表明布隆过滤器编码可作为高效通用的预处理表示，保留学习任务所需的相似性结构，并提供一定数据混淆能力。
原文摘要 · Abstract (English)
We present a method that uses a Bloom filter transform to preprocess data for machine learning. Each sample is encoded into a compact bit-array representation using hash-based encoding, producing a fixed-length feature space that reduces memory usage and obfuscates original feature values. The encoding does not rely on keyed hashing; however, a key can optionally be used to control the mapping and would be required to reproduce the representation. We evaluate the approach on six datasets spanning text, time-series, tabular, and image domains: SMS Spam Collection, ECG200, Adult 50K, CDC Diabetes, MNIST, and Fashion MNIST. Four classifiers are considered: Extreme Gradient Boosting, Deep Neural Networks, Convolutional Neural Networks, and Logistic Regression. Results show that models trained on Bloom filter encodings achieve performance comparable to models trained on raw data or standard dimensionality reduction techniques across several datasets, while providing consistent memory savings. These findings suggest that Bloom filter encodings can serve as an efficient, general-purpose pre-processing representation that preserves useful similarity structure for learning tasks while providing a degree of data obfuscation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。