A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
-
Updated
Apr 7, 2025 - Python
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
State-of-the-art neural cardinality estimators for join queries
TIP2022 Adaptive Boosting (AdaBoost) for Domain Adaptation ? 🤷♀️ Why not ! 🙆♀️
Reinforced Data Sampling
This project aims to analyze the citation network of arXiv papers. We use Python to clean the data and create a Neo4j network to visualize and analyze the citation relationships between arXiv papers.
Code and Data for paper: Variation across Scales: Measurement Fidelity under Twitter Data Sampling (ICWSM '20)
Add a description, image, and links to the data-sampling topic page so that developers can more easily learn about it.
To associate your repository with the data-sampling topic, visit your repo's landing page and select "manage topics."