Scalable Graph Hashing with Feature Transformation Model and Leamning Complexity Analysis o Initialization 。P(x)andQ(X):O(dn) Kernel initialization:O(dmn +mn) ·A1andZ:O(d+2)mn) ·Main procedure 。O(c(mn+m2)+m3) Typically,m,d,c will be much less than n. Hence,the time complexity is O(n).Furthermore,the storage complexity is also O(n). 日卡0”三1元，互Q0 Li (http://cs.nju.edu.cn/lvj) Learning to Hash LAMDA,CS.NJU 30/43Scalable Graph Hashing with Feature Transformation Model and Learning Complexity Analysis Initialization P(X) and Q(X): O(dn) Kernel initialization: O(dmn + mn) A1 and Z: O((d + 2)mn) Main procedure O(c(mn + m2 ) + m3 ) Typically, m, d, c will be much less than n. Hence, the time complexity is O(n). Furthermore, the storage complexity is also O(n). Li (http://cs.nju.edu.cn/lwj) Learning to Hash LAMDA, CS, NJU 30 / 43