K-NN graph

tasks:

1. unsupervised knn

https://scikit-learn.org/stable/modules/neighbors.html#unsupervised-neighbors

2. isomap

3. largevis

4. line

5.umap

 

1. how to construct a KNN graph?

常見的方法一般有三類: i. space-partitioning trees; ii. locality sensitive hashing; iii. neighbour exploring techniques. 

 

Reference:

1. Nearest neighbor graph;

2. 聚類算法實踐（二）——譜聚類、Chameleon聚類  waiting to read. 

3. K-dimension tree, k-d tree. Use the k-d tree to implement knn algorithm. 

【量化課堂】kd 樹算法之思路篇

【數學】kd 樹算法之詳細篇