research-article

Open access

Reconfigurable Inverted Index

Authors:

Shin'ichi SatohAuthors Info & Claims

MM '18: Proceedings of the 26th ACM international conference on Multimedia

Pages 1715 - 1723

https://doi.org/10.1145/3240508.3240630

Published: 15 October 2018 Publication History

Abstract

Existing approximate nearest neighbor search systems suffer from two fundamental problems that are of practical importance but have not received sufficient attention from the research community. First, although existing systems perform well for the whole database, it is difficult to run a search over a subset of the database. Second, there has been no discussion concerning the performance decrement after many items have been newly added to a system. We develop a reconfigurable inverted index (Rii) to resolve these two issues. Based on the standard IVFADC system, we design a data layout such that items are stored linearly. This enables us to efficiently run a subset search by switching the search method to a linear PQ scan if the size of a subset is small. Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system. Extensive comparisons show that Rii achieves a comparable performance with state-of-the art systems such as Faiss.

Supplementary Material

ZIP File (fp0587.zip)

Supplementary Material for "Reconfigurable Inverted Index"

Download
415.24 KB

References

[1]

Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, and Ludwig Schmidt. 2015. Practical and Optimal LSH for Angular Distance. In Proc. NIPS .

Digital Library

[2]

Fabien André, Anne-Marie Kermarrec, and Nicolas Le Scouarnec. 2015. Cache Locality is Not Enough: High-performance Nearest Neighbor Search with Product Quantization Fast Scan. In Proc. VLDB .

Digital Library

[3]

Fabien André, Anne-Marie Kermarrec, and Nicolas Le Scouarnec. 2017. Accelerated Nearest Neighbor Search with Quick ADC. In Proc. ICMR .

Digital Library

[4]

Martin Aumüller, Erik Bernhardsson, and Alexander Faithfull. 2017. ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms. In Proc. SISAP .

[5]

Artem Babenko and Victor Lemitsky. 2017. AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding. In Proc. IEEE ICCV .

[6]

Artem Babenko and Victor Lempitsky. 2014. Additive Quantization for Extreme Vector Compression. In Proc. IEEE CVPR .

Digital Library

[7]

Artem Babenko and Victor Lempitsky. 2015a. The Inverted Multi-Index. IEEE TPAMI, Vol. 37, 6 (2015), 1247--1260.

[8]

Artem Babenko and Victor Lempitsky. 2015b. Tree Quantization for Large-Scale Similarity Search and Classification. In Proc. IEEE CVPR .

[9]

Artem Babenko and Victor Lempitsky. 2016. Efficient Indexing of Billion-Scale Datasets of Deep Descriptors. In Proc. IEEE CVPR .

[10]

Dmitry Baranchuk, Artem Babenko, and Yury Malkov. 2018. Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors. In Proc. ECCV .

[11]

Erik Bernhardsson. 2018. Annoy. https://github.com/spotify/annoy.

[12]

Erik Bernhardsson, Martin Aumüller, and Alexander Faithfull. 2018. ann-benchmarks. https://github.com/erikbern/ann-benchmarks.

[13]

Davis W. Blalock and John V. Guttag. 2017. Bolt: Accelerated Data Mining with Fast Vector Compression. In Proc. ACM KDD .

Digital Library

[14]

Leonid Boytsov and Bilegsaikhan Naidan. 2013. Engineering Efficient and Effective Non-metric Space Library. In Proc. SISAP .

Digital Library

[15]

Mayur Datar, Nicole Immorlica, Piotr Indyk, and Vahab S. Mirrokni. 2004. Locality-Sensitive Hashing Scheme Based on p-Stable Distributions. In Proc. SCG .

Digital Library

[16]

Matthijs Douze, Hervé Jégou, and Florent Perronnin. 2016. Polysemous Codes. In Proc. ECCV .

[17]

Matthijs Douze, Alexandre Sablayrolles, and Hervé Jégou. 2018. Link and code: Fast indexing with graphs and compact regression codes. In Proc. IEEE CVPR .

[18]

Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2014. Optimized Product Quantization. IEEE TPAMI, Vol. 36, 4 (2014), 744--755.

Digital Library

[19]

Gylfi Þór Gudmundsson, Björn Þór Jónsson, Laurent Amsaleg, and Michael J. Franklin. 2018. Prototyping a Web-Scale Multimedia Retrieval Service Using Spark. ACM TOMM, Vol. 14, 3s (2018), 65:1--65:24.

Digital Library

[20]

Jae-Pil Heo, Zhe Lin, Xiaohui Shen, Jonathan Brandt, and Sung-Eui Yoon. 2016. Shortlist Selection With Residual-Aware Distance Estimator for K-Nearest Neighbor Search. In Proc. IEEE CVPR .

[21]

Jae-Pil Heo, Zhe Lin, and Sung-Eui Yoon. 2014. Distance Encoded Product Quantization. In Proc. IEEE CVPR .

Digital Library

[22]

Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proc. IEEE CVPR .

[23]

Masakazu Iwamura, Tomokazu Sato, and Koichi Kise. 2013. What Is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search?. In Proc. IEEE ICCV .

Digital Library

[24]

Himalaya Jain, Patrick Pérez, Rémi Gribonval, Joaquin Zepeda, and Hervé Jégou. 2016. Approximate Search with Quantized Sparse Representations. In Proc. ECCV .

[25]

Hervé Jégou, Matthijs Douze, and Jeff Johnson. 2018. Faiss. https://github.com/facebookresearch/faiss.

[26]

Hervé Jégou, Matthijis Douze, and Cordelia Schmid. 2011a. Product Quantization for Nearest Neighbor Search. IEEE TPAMI, Vol. 33, 1 (2011), 117--128.

Digital Library

[27]

Hervé Jégou, Romain Tavenard, Matthijs Douze, and Laurent Amsaleg. 2011b. Searching in One Billion Vectors: Re-rank with Source Coding. In Proc. IEEE ICASSP .

[28]

Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2017. Billion-scale Similarity Search with GPUs. CoRR, Vol. abs/1702.08734 (2017).

[29]

Yannis Kalantidis and Yannis Avrithis. 2014. Locally Optimized Product Quantization for Approximate Nearest Neighbor Search. In Proc. IEEE CVPR .

Digital Library

[30]

Yingfan Liu, Hong Cheng, and Jiangtao Cui. 2017. PQBF: I/O-Efficient Approximate Nearest Neighbor Search by Product Quantization. In Proc. CIKM .

Digital Library

[31]

Qin Lv, William Josephson, Zhe Wang, Moses Charikar, and Kai Li. 2007. Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search. In Proc. VLDB .

Digital Library

[32]

Yury Malkov, Alexander Ponomarenko, Andrey Logvinov, and Vladimir Krylov. 2014. Approximate Nearest Neighbor Algorithm Based on Navigable Small World Graphs. Inf. Syst., Vol. 45 (2014), 61--68.

[33]

Yury A. Malkov and Dmitry A. Yashunin. 2016. Efficient and Robust Approximate Nearest Neighbor Search using Hierarchical Navigable Small World Graphs. CoRR, Vol. abs/1603.09320 (2016).

[34]

Julieta Martinez, Joris Clement, Holger H. Hoos, and James J. Little. 2016. Revisiting Additive Quantization. In Proc. ECCV .

[35]

Yusuke Matsui, Keisuke Ogaki, Toshihiko Yamasaki, and Kiyoharu Aizawa. 2017. PQk-means: Billion-scale Clustering for Product-quantized Codes. In Proc. MM .

Digital Library

[36]

Yusuke Matsui, Yusuke Uchida, Hervé Jégou, and Shin'ichi Satoh. 2018a. A Survey of Product Quantization. ITE Transactions on Media Technology and Applications, Vol. 6, 1 (2018), 2--10.

[37]

Yusuke Matsui, Toshihiko Yamasaki, and Kiyoharu Aizawa. 2018b. PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables. IEEE TMM, Vol. 20, 7 (2018), 1809--1822.

[38]

Marius Muja and David G. Lowe. 2014. Scalable Nearest Neighbor Algorithms for High Dimensional Data. IEEE TPAMI, Vol. 36, 11 (2014), 2227--2240.

[39]

Bilegsaikhan Naidan, Leonid Boytsov, Yury Malkov, David Novak, and Ben Frederickson. 2018. Non-Metric Space Library (NMSLIB). https://github.com/searchivarius/nmslib.

[40]

Mohammad Norouzi and David J. Fleet. 2013. Cartesian k-means. In Proc. IEEE CVPR .

Digital Library

[41]

Ilya Razenshteyn and Ludwig Schmidt. 2018. FALCONN - FAst Lookups of Cosine and Other Nearest Neighbors. https://github.com/FALCONN-LIB/FALCONN.

[42]

Eleftherios Spyromitros-Xioufis, Symeon Papadopoulos, Ioannis (Yiannis) Kompatsiaris, Grigorios Tsoumakas, and Ioannis Vlahavas. 2014. A Comprehensive Study Over VLAD and Product Quantization in Large-Scale Image Retrieval. IEEE TMM, Vol. 16, 6 (2014), 1713--1728.

[43]

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going Deeper With Convolutions. In Proc. IEEE CVPR .

[44]

Jianfeng Wang, Jingdong Wang, Jingkuan Song, Xin-Shun Xu, Heng Tao Shen, and Shipeng Li. 2015. Optimized Cartesian K-Means. IEEE TKDE, Vol. 27, 1 (2015), 180--192.

[45]

Patrick Wieschollek, Oliver Wang, Alexander Sorkine-Hornung, and Hendrik P. A. Lensch. 2016. Efficient Large-Scale Approximate Nearest Neighbor Search on the GPU. In Proc. IEEE CVPR .

[46]

Yan Xia, Kaiming He, Fang Wen, and Jian Sun. 2013. Joint Inverted Indexing. In Proc. IEEE ICCV .

Digital Library

[47]

Jialiang Zhang, Soroosh Khoram, and Jing Li. 2018. Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA. In Proc. IEEE CVPR .

[48]

Ting Zhang, Chao Du, and Jingdong Wang. 2014. Composite Quantization for Approximate Nearest Neighbor Search. In Proc. ICML .

Digital Library

[49]

Ting Zhang, Guo-Jun Qi, Jinhui Tang, and Jingdong Wang. 2015. Sparse Composite Quantization. In Proc. IEEE CVPR .

Cited By

Deguchi HWatanabe TMatsui YUtiyama MTanaka HSumita E(2024)Subset Retrieval Nearest Neighbor Machine TranslationJournal of Natural Language Processing10.5715/jnlp.31.37431:2(374-406)Online publication date: 2024
https://doi.org/10.5715/jnlp.31.374
Xu YGao JGou YLong CJensen C(2024)iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor SearchProceedings of the ACM on Management of Data10.1145/36988142:6(1-26)Online publication date: 20-Dec-2024
https://dl.acm.org/doi/10.1145/3698814
Zuo CQiao MZhou WLi FDeng D(2024)SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor SearchProceedings of the ACM on Management of Data10.1145/36393242:1(1-26)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639324
Show More Cited By

Index Terms

Reconfigurable Inverted Index
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Visual content-based indexing and retrieval
2. Information systems
  1. Information retrieval
    1. Search engine architectures and scalability
      1. Search engine indexing
    2. Specialized information retrieval
      1. Multimedia and multimodal retrieval
  2. Information systems applications
    1. Data mining
      1. Nearest-neighbor search

Recommendations

HDIdx

Fast Nearest Neighbor (NN) search is a fundamental challenge in large-scale data processing and analytics, particularly for analyzing multimedia contents which are often of high dimensionality. Instead of using exact NN search, extensive research ...
Selective K-means Tree Search
MM '15: Proceedings of the 23rd ACM international conference on Multimedia

In object recognition and image retrieval, an inverted indexing method is used to solve the approximate nearest neighbor search problem. In these tasks, inverted indexing provides a nonexhaustive solution to large-scale search. However, a problem of ...
The Inverted Multi-Index
A new data structure for efficient similarity search in very large datasets of high-dimensional vectors is introduced. This structure called the inverted multi-index generalizes the inverted index idea by replacing the standard quantization within ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '18: Proceedings of the 26th ACM international conference on Multimedia

October 2018

2167 pages

ISBN:9781450356657

DOI:10.1145/3240508

General Chairs:
Susanne Boll
University of Oldenburg, Germany
,
Kyoung Mu Lee
Seoul National University, Korea
,
Jiebo Luo
University of Rochester, USA
,
Wenwu Zhu
Tsinghua University, China
,
Program Chairs:
Hyeran Byun
Yonsei University, Korea
,
Chang Wen Chen
State Univ. Of New York at Buffalo, USA
,
Rainer Lienhart
University of Augsburg, Germany
,
Tao Mei
JD AI, China

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 October 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

JST ACT-I

Conference

MM '18

Sponsor:

SIGMM

MM '18: ACM Multimedia Conference

October 22 - 26, 2018

Seoul, Republic of Korea

Acceptance Rates

MM '18 Paper Acceptance Rate 209 of 757 submissions, 28%;

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
1,494
Total Downloads

Downloads (Last 12 months)179
Downloads (Last 6 weeks)25

Reflects downloads up to 16 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Deguchi HWatanabe TMatsui YUtiyama MTanaka HSumita E(2024)Subset Retrieval Nearest Neighbor Machine TranslationJournal of Natural Language Processing10.5715/jnlp.31.37431:2(374-406)Online publication date: 2024
https://doi.org/10.5715/jnlp.31.374
Xu YGao JGou YLong CJensen C(2024)iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor SearchProceedings of the ACM on Management of Data10.1145/36988142:6(1-26)Online publication date: 20-Dec-2024
https://dl.acm.org/doi/10.1145/3698814
Zuo CQiao MZhou WLi FDeng D(2024)SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor SearchProceedings of the ACM on Management of Data10.1145/36393242:1(1-26)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639324
Zhu SPan LXiong D(2024)FEDS-ICLInformation Processing and Management: an International Journal10.1016/j.ipm.2024.10382561:5Online publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1016/j.ipm.2024.103825
Deguchi H(2023)Subset Retrieval Nearest Neighbor Machine TranslationSubset Retrieval Nearest Neighbor Machine TranslationJournal of Natural Language Processing10.5715/jnlp.30.124530:4(1245-1250)Online publication date: 2023
https://doi.org/10.5715/jnlp.30.1245
Zuo CDeng D(2023)ARKGraph: All-Range Approximate K-Nearest-Neighbor GraphProceedings of the VLDB Endowment10.14778/3603581.360360116:10(2645-2658)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.14778/3603581.3603601
Chen WMa XZeng JDuan YZhong G(2021)Hierarchical quantization for billion-scale similarity retrieval on GPUsComputers & Electrical Engineering10.1016/j.compeleceng.2021.10700290(107002)Online publication date: Mar-2021
https://doi.org/10.1016/j.compeleceng.2021.107002

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents