Bio-Inspired Hashing for Unsupervised Similarity Search

Chaitanya Ryali, John Hopfield, Leopold Grinberg, Dmitry Krotov
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:8295-8306, 2020.

Abstract

The fruit fly Drosophila’s olfactory circuit has inspired a new locality sensitive hashing (LSH) algorithm, FlyHash. In contrast with classical LSH algorithms that produce low dimensional hash codes, FlyHash produces sparse high-dimensional hash codes and has also been shown to have superior empirical performance compared to classical LSH algorithms in similarity search. However, FlyHash uses random projections and cannot learn from data. Building on inspiration from FlyHash and the ubiquity of sparse expansive representations in neurobiology, our work proposes a novel hashing algorithm BioHash that produces sparse high dimensional hash codes in a data-driven manner. We show that BioHash outperforms previously published benchmarks for various hashing methods. Since our learning algorithm is based on a local and biologically plausible synaptic plasticity rule, our work provides evidence for the proposal that LSH might be a computational reason for the abundance of sparse expansive motifs in a variety of biological systems. We also propose a convolutional variant BioConvHash that further improves performance. From the perspective of computer science, BioHash and BioConvHash are fast, scalable and yield compressed binary representations that are useful for similarity search.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-ryali20a, title = {Bio-Inspired Hashing for Unsupervised Similarity Search}, author = {Ryali, Chaitanya and Hopfield, John and Grinberg, Leopold and Krotov, Dmitry}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {8295--8306}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/ryali20a/ryali20a.pdf}, url = {https://proceedings.mlr.press/v119/ryali20a.html}, abstract = {The fruit fly Drosophila’s olfactory circuit has inspired a new locality sensitive hashing (LSH) algorithm, FlyHash. In contrast with classical LSH algorithms that produce low dimensional hash codes, FlyHash produces sparse high-dimensional hash codes and has also been shown to have superior empirical performance compared to classical LSH algorithms in similarity search. However, FlyHash uses random projections and cannot learn from data. Building on inspiration from FlyHash and the ubiquity of sparse expansive representations in neurobiology, our work proposes a novel hashing algorithm BioHash that produces sparse high dimensional hash codes in a data-driven manner. We show that BioHash outperforms previously published benchmarks for various hashing methods. Since our learning algorithm is based on a local and biologically plausible synaptic plasticity rule, our work provides evidence for the proposal that LSH might be a computational reason for the abundance of sparse expansive motifs in a variety of biological systems. We also propose a convolutional variant BioConvHash that further improves performance. From the perspective of computer science, BioHash and BioConvHash are fast, scalable and yield compressed binary representations that are useful for similarity search.} }
Endnote
%0 Conference Paper %T Bio-Inspired Hashing for Unsupervised Similarity Search %A Chaitanya Ryali %A John Hopfield %A Leopold Grinberg %A Dmitry Krotov %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-ryali20a %I PMLR %P 8295--8306 %U https://proceedings.mlr.press/v119/ryali20a.html %V 119 %X The fruit fly Drosophila’s olfactory circuit has inspired a new locality sensitive hashing (LSH) algorithm, FlyHash. In contrast with classical LSH algorithms that produce low dimensional hash codes, FlyHash produces sparse high-dimensional hash codes and has also been shown to have superior empirical performance compared to classical LSH algorithms in similarity search. However, FlyHash uses random projections and cannot learn from data. Building on inspiration from FlyHash and the ubiquity of sparse expansive representations in neurobiology, our work proposes a novel hashing algorithm BioHash that produces sparse high dimensional hash codes in a data-driven manner. We show that BioHash outperforms previously published benchmarks for various hashing methods. Since our learning algorithm is based on a local and biologically plausible synaptic plasticity rule, our work provides evidence for the proposal that LSH might be a computational reason for the abundance of sparse expansive motifs in a variety of biological systems. We also propose a convolutional variant BioConvHash that further improves performance. From the perspective of computer science, BioHash and BioConvHash are fast, scalable and yield compressed binary representations that are useful for similarity search.
APA
Ryali, C., Hopfield, J., Grinberg, L. & Krotov, D.. (2020). Bio-Inspired Hashing for Unsupervised Similarity Search. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:8295-8306 Available from https://proceedings.mlr.press/v119/ryali20a.html.

Related Material