Approximate nearest neighbour (ANN) search is an essential component of search engines, recommendation systems, etc. Many recent works focus on learning-based data-distribution-dependent hashing and achieve good retrieval performance. However, due to increasing demand for users' privacy and security, we often need to remove users' data information from Machine Learning (ML) models to satisfy specific privacy and security requirements. This need requires the ANN search algorithm to support fast online data deletion and insertion. Current learning-based hashing methods need retraining the hash function, which is prohibitable due to the vast time-cost of large-scale data. To address this problem, we propose a novel data-dependent hashing method named unfolded self-reconstruction locality-sensitive hashing (USR-LSH). Our USR-LSH unfolded the optimization update for instance-wise data reconstruction, which is better for preserving data information than data-independent LSH. Moreover, our USR-LSH supports fast online data deletion and insertion without retraining. To the best of our knowledge, we are the first to address the machine unlearning of retrieval problems. Empirically, we demonstrate that USR-LSH outperforms the state-of-the-art data-distribution-independent LSH in ANN tasks in terms of precision and recall. We also show that USR-LSH has significantly faster data deletion and insertion time than learning-based data-dependent hashing.

翻译：近似最近邻（ANN）搜索是搜索引擎、推荐系统等领域的核心组件。近期多项研究聚焦于基于学习的数据分布依赖型哈希方法，并取得了优异的检索性能。然而，随着用户隐私与安全需求的日益增长，我们常需从机器学习模型中移除用户数据信息，以满足特定的隐私与安全要求。这一需求促使ANN搜索算法必须支持快速的在线数据删除与插入。当前基于学习的哈希方法需要重新训练哈希函数，而大规模数据带来的巨大时间成本使得这一方案不可行。为解决该问题，我们提出一种新型数据依赖型哈希方法——展开式自重构局部敏感哈希（USR-LSH）。USR-LSH通过展开优化迭代实现实例级数据重构，相比数据无关的LSH能更好地保留数据信息。此外，USR-LSH支持无需重训练的快速在线数据删除与插入。据我们所知，这是首个面向检索问题中机器遗忘的研究。实验表明，在ANN任务中，USR-LSH在精确率与召回率上均优于当前最优的数据分布无关型LSH方法。同时，与基于学习的数据依赖型哈希方法相比，USR-LSH在数据删除与插入速度上具有显著优势。