Scalable Graph Hashing with Feature Transformation Model and Leamning Notation X={x1,...,xn)TE Rnxd:n data points. obi[+1,-1e:binary code of point xi. o bi [h1(xi),...,he(xi)],where hk(x)denotes hash function. Pairwise similarity metric defined as:S=e-llx-xle/p∈(0，l刂 日卡三4元，互Q0 Li (http://cs.nju.edu.cn/lwj) Learning to Hash LAMDA,CS.NJU 22 /43Scalable Graph Hashing with Feature Transformation Model and Learning Notation X = {x1, . . . , xn} T ∈ R n×d : n data points. bi ∈ {+1, −1} c : binary code of point xi . bi = [h1(xi), . . . , hc(xi)]T , where hk(x) denotes hash function. Pairwise similarity metric defined as: Sij = e −||xi−xj ||2 F /ρ ∈ (0, 1] Li (http://cs.nju.edu.cn/lwj) Learning to Hash LAMDA, CS, NJU 22 / 43