About the knn graph

[xuebaliang]

hello, recently I read your paper and it is a great work! But I have some question, does the knn graph you calculate lastly only give weight for nearest k nodes for every node?for others is it zero? If so, how does the width sigma of gaussian kernel for each point in the high dimension space determine? And I look for them in your code, but unfortunately I can't find it. Can you tell me a little more? Thanks.