Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Locality Sensitive Hashing at Lyst
Search
Maciej Kula
July 24, 2015
Programming
0
1.3k
Locality Sensitive Hashing at Lyst
Description of the intuition behind locality sensitive hashing and its application at Lyst.
Maciej Kula
July 24, 2015
Tweet
Share
More Decks by Maciej Kula
See All by Maciej Kula
Implicit and Explicit Recommender Systems
maciejkula
0
2.9k
Binary Embeddings For Efficient Ranking
maciejkula
0
680
Rust for Python Native Extensions
maciejkula
0
470
Hybrid Recommender Systems at PyData Amsterdam 2016
maciejkula
5
2.7k
Recommendations under sparsity
maciejkula
1
360
Metadata Embeddings for User and Item Cold-start Recommendations
maciejkula
2
960
Other Decks in Programming
See All in Programming
奥深くて厄介な「改行」と仲良くなる20分
oguemon
1
460
Honoアップデート 2025年夏
yusukebe
1
920
2025 年のコーディングエージェントの現在地とエンジニアの仕事の変化について
azukiazusa1
19
10k
さようなら Date。 ようこそTemporal! 3年間先行利用して得られた知見の共有
8beeeaaat
2
1.4k
🔨 小さなビルドシステムを作る
momeemt
3
660
「手軽で便利」に潜む罠。 Popover API を WCAG 2.2の視点で安全に使うには
taitotnk
0
780
Improving my own Ruby thereafter
sisshiki1969
1
160
AIでLINEスタンプを作ってみた
eycjur
1
230
Oracle Database Technology Night 92 Database Connection control FAN-AC
oracle4engineer
PRO
1
430
Design Foundational Data Engineering Observability
sucitw
3
180
Go言語での実装を通して学ぶLLMファインチューニングの仕組み / fukuokago22-llm-peft
monochromegane
0
120
旅行プランAIエージェント開発の裏側
ippo012
2
870
Featured
See All Featured
[RailsConf 2023] Rails as a piece of cake
palkan
57
5.8k
Done Done
chrislema
185
16k
A designer walks into a library…
pauljervisheath
207
24k
GitHub's CSS Performance
jonrohan
1032
460k
Optimising Largest Contentful Paint
csswizardry
37
3.4k
The Power of CSS Pseudo Elements
geoffreycrofte
77
5.9k
Product Roadmaps are Hard
iamctodd
PRO
54
11k
Making Projects Easy
brettharned
117
6.4k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
23
1.4k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.5k
Rebuilding a faster, lazier Slack
samanthasiow
83
9.2k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.1k
Transcript
Speeding up search with locality sensitive hashing. by Maciej Kula
Hi, I’m Maciej Kula. @maciej_kula
We collect the world of fashion into a customisable shopping
experience.
Given a point, find other points close to it. Nearest
neighbour search… 4
None
At Lyst we use it for… 1.) Image Search 2.)
Recommendations 6
Convert image to points in space (vectors) & use nearest
neighbour search to get similar images. 1. Image Search (-0.3, 2.1, 0.5)
Super useful for deduplication & search.
Convert products and users to points in space & use
nearest neighbour search to get related products for the user. 2. Recommendations user = (-0.3, 2.1, 0.5) product = (5.2, 0.3, -0.5)
Great, but…
11 80 million We have images
12 9 million We have products
Exhaustive nearest neighbour search is too slow.
Locality sensitive hashing to the rescue! Use a hash table.
Pick a hash function that puts similar points in the same bucket. Only search within the bucket.
We use Random Projection Forests
Partition by splitting on random vectors
Partition by splitting on random vectors
Partition by splitting on random vectors
Partition by splitting on random vectors
Partition by splitting on random vectors
Points to note Keep splitting until the nodes are small
enough. Median splits give nicely balanced trees. Build a forest of trees.
Why do we need a forest? Some partitions split the
true neighbourhood of a point. Because partitions are random, other trees will not repeat the error. Build more trees to trade off query speed for precision.
LSH in Python annoy, Python wrapper for C++ code. LSHForest,
part of scikit-learn FLANN, an auto-tuning ANN index
But… LSHForest is slow. FLANN is a pain to deploy.
annoy is great, but can’t add points to an existing index.
So we wrote our own.
github.com/lyst/rpforest pip install rpforest
rpforest Quite fast. Allows adding new items to the index.
Does not require us to store points in memory.
We use it in conjunction with PostgreSQL Send the query
point to the ANN index. Get ANN row ids back Plug them into postgres for filtering Final scoring done in postgres using C extensions.
Side note: postgres is awesome. Arrays & custom functions in
C
Gives us a fast and reliable ANN service 100x speed-up
with 0.6 10-NN precision Allows us to serve real-time results All on top of a real database.
thank you @maciej_kula