Scalable k-nearest neighbor graph construction based on greedy filtering

Authors:
Youngki Park;Sungchan Park;Sang-goo Lee;Woosung Jung
Affiliations:
Seoul National University, Seoul, South Korea;Seoul National University, Seoul, South Korea;Seoul National University, Seoul, South Korea;Chungbuk National University, Cheongju-si, Chungcheongbuk-do, South Korea
Venue:
Proceedings of the 22nd international conference on World Wide Web companion
Year:
2013

Citing 4
Cited 0

Scaling up all pairs similarity search

Proceedings of the 16th international conference on World Wide Web
Top-k Set Similarity Joins

ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
An efficient similarity join algorithm with cosine similarity predicate

DEXA'10 Proceedings of the 21st international conference on Database and expert systems applications: Part II
Efficient k-nearest neighbor graph construction for generic similarity measures

Proceedings of the 20th international conference on World wide web

Quantified Score

Hi-index	0.00

Visualization

Abstract

K-Nearest Neighbor Graph (K-NNG) construction is a primitive operation in the field of Information Retrieval and Recommender Systems. However, existing approaches to K-NNG construction do not perform well as the number of nodes or dimensions scales up. In this paper, we present greedy filtering, an effcient and scalable algorithm for selecting the candidates for nearest neighbors by matching only the dimensions of large values. The experimental results show that our K-NNG construction scheme, based on greedy filtering, guarantees a high recall while also being 5 to 6 times faster than state-of-the-art algorithms for large, high-dimensional data.