On the Merge of k-NN Graph
share
K-nearest neighbor graph is the fundamental data structure in many disciplines such as information retrieval, data-mining, pattern recognition and machine learning, etc. In the literature, considerable research has been focusing on how to efficiently build an approximate k-nearest neighbor graph (k-NN graph) for a fixed dataset. Unfortunately, a closely related issue to the approximate k-NN graph construction has been long overlooked. Namely, few literature covers about how to merge existing k-NN graphs. In this paper, we address the k-NN graph merge issue of two different scenarios. One one hand, we address the problem of merging two existing graphs into one by the proposed peer merge. This makes parallel approximate k-NN graph computation in large-scale become possible. On the other hand, the problem of merging a raw set into a built k-NN graph is also addressed by the proposed joint merge. It enables the approximate k-NN graph to be built incrementally. Thus it supports approximate k-NN graph construction for an open set. Moreover, deriving from joint merge, an hierarchical graph construction approach is presented. With the support of produced graph hierarchy, superior performance is observed on the large-scale NN search task across various data types and various data dimensions, under different distance measures.
READ FULL TEXT