Biblio

K-Nearest Neighbor (k-NN) search is one of the most commonly used approaches for similarity search. It finds extensive applications in machine learning and data mining. This era of big data warrants efficiently scaling k-NN search algorithms for billion-scale datasets with high dimensionality. In this paper, we propose a solution towards this end where we use vantage point trees for partitioning the dataset across multiple processes and exploit an existing graph-based sequential approximate k-NN search algorithm called HNSW (Hierarchical Navigable Small World) for searching locally within a process. Our hybrid MPI-OpenMP solution employs techniques including exploiting MPI one-sided communication for reducing communication times and partition replication for better load balancing across processes. We demonstrate computation of k-NN for 10,000 queries in the order of seconds using our approach on 8000 cores on a dataset with billion points in an 128-dimensional space. We also show 10X speedup over a completely k-d tree-based solution for the same dataset, thus demonstrating better suitability of our solution for high dimensional datasets. Our solution shows almost linear strong scaling.

A fundamental recurring task in many machine learning applications is the search for the Nearest Neighbor in high dimensional metric spaces. Towards answering queries in large scale problems, state-of-the-art methods employ Approximate Nearest Neighbors (ANN) search, a search that returns the nearest neighbor with high probability, as well as techniques that compress the dataset. Product-Quantization (PQ) based ANN search methods have demonstrated state-of-the-art performance in several problems, including classification, regression and information retrieval. The dataset is encoded into a Cartesian product of multiple low-dimensional codebooks, enabling faster search and higher compression. Being intrinsically parallel, PQ-based ANN search approaches are amendable for hardware acceleration. This paper proposes a novel Hierarchical PQ (HPQ) based ANN search method as well as an FPGA-tailored architecture for its implementation that outperforms current state of the art systems. HPQ gradually refines the search space, reducing the number of data compares and enabling a pipelined search. The mapping of the architecture on a Stratix 10 FPGA device demonstrates over ×250 speedups over current state-of-the-art systems, opening the space for addressing larger datasets and/or improving the query times of current systems.

With the increasing popularity of cloud storage services, many individuals and enterprises start to move their local data to the clouds. To ensure their privacy and data security, some cloud service users may want to encrypt their data before outsourcing them. However, this impedes efficient data utilities based on the plain text search. In this paper, we study how to construct a secure index that supports both efficient index updating and similarity search. Using the secure index, users are able to efficiently perform similarity searches tolerating input mistakes and update the index when new data are available. We formally prove the security of our proposal and also perform experiments on real world data to show its efficiency.