Modeling Winner-Take-All Competition in Sparse Binary Projections
This work provides a practical tool for real-world applications, offering incremental improvements in similarity search tasks.
The authors tackled the problem of similarity search by developing supervised and unsupervised sparse binary projection models with Winner-Take-All competition, reporting significantly improved results in both search accuracies and running speed over state-of-the-art methods.
Inspired by the advances in biological science, the study of sparse binary projection models has attracted considerable recent research attention. The models project dense input samples into a higher-dimensional space and output sparse binary data representations after the Winner-Take-All competition, subject to the constraint that the projection matrix is also sparse and binary. Following the work along this line, we developed a supervised-WTA model when training samples with both input and output representations are available, from which the optimal projection matrix can be obtained with a simple, effective yet efficient algorithm. We further extended the model and the algorithm to an unsupervised setting where only the input representation of the samples is available. In a series of empirical evaluation on similarity search tasks, the proposed models reported significantly improved results over the state-of-the-art methods in both search accuracies and running speed. The successful results give us strong confidence that the work provides a highly practical tool to real world applications.