Abstract: Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities.Although promising, the association between the computation cost and the number of identities in the dataset remains linear only with a reduced ratio. A shared characteristic among available FR methods is the employment of atomic scalar labels during training. Consequently, the input to label matching is through a dot product between the feature vector of the input and the Softmax centroids. In this work, we present a simple yet effective method that substitutes scalar labels with structured identity code, \ie, a sequence of integers. Specifically, we propose a tokenization scheme that transforms atomic scalar labels into structured identity codes. Then, we train an FR backbone to predict the code for each input instead of its scalar label. As a result, the associated computational cost becomes logarithmic \wrt number of identities. We demonstrate the benefits of the proposed method by conducting experiments on LFW, CFP-FP, CPLFW, CALFW, AgeDB, IJB-B, and IJB-C using different backbone network architectures. In particular, with less training computational load, our method outperforms its competitors by 1.52\%, and 0.6\% at TAR@FAR$=1e-4$ on IJB-B and IJB-C, respectively.