HEXA: A Disjoint-Subgraph-Based Indexing Framework for Approximate Nearest Neighbor Search at Billion Scale
HEXA is introduced, a disjoint-subgraph-based indexing framework that partitions the dataset into disjoint clusters and constructs refined proximity subgraphs independently on GPUs and achieves up to 14.7 times higher query throughput at the same recall levels compared with various indexing methods.