PilotScope is a middleware to bridge the gaps of deploying AI4DB (Artificial Intelligence for Databases) algorithms into actual database systems.

Neural Relation Understanding: neural cardinality estimators for tabular data

Implementation of DeepDB: Learn from Data, not from Queries!

State-of-the-art neural cardinality estimators for join queries

A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation

A pytorch implementation for FACE: A Normalizing Flow based Cardinality Estimator

A Python library for efficient feature ranking and selection on sparse data sets.

Fast Cardinality Estimation of Multi-Join Queries Using Sketches

Code for Local Deep Learning Models for Cardinality Estimation

An implementation of the algorithms presented in the paper "Cardinality Estimation Done Right: Index-Based Join Sampling"

[VLDB'22] Cardinality Estimation of Approximate Substring Queries using Deep Learning.

UltraLogLog: A Practical and More Space-Efficient Alternative to HyperLogLog for Approximate Distinct Counting

Learned model to estimate number of distinct values (NDV) of a population using a small sample.

Code for variable skipping ICML 2020 paper

Scalable Join Cardinality Estimaitor

Simpli-Squared is a statistics-free join ordering algorithm Without Cardinality Estimates.

python implementations of the Flajolet-Martin, LogLog, SuperLogLog, and HyperLogLog cardinality estimation algorithms, specifically used to estimate the cardinality of unique traffic violations in NYC in the 2019 fiscal year

Reference implementation of the Affirmative Sampling algorithm by Jérémie Lumbroso and Conrado Martínez (2022). 🍀

Updated code for different query featurizations for MSCN

This repository provides streaming algorithms that can be used for monitoring large-scale data streams.