Optimizing Ranking Measures for Compact Binary Code Learning

Abstract. Hashing has proven a valuable tool for large-scale informa-tion retrieval. Despite much success, existing hashing methods optimize over simple objectives such as the reconstruction error or graph Lapla-cian related loss functions, instead of the performance evaluation crite-ria of interest—multivariate performance measures such as the AUC and NDCG. Here we present a general framework (termed StructHash) that allows one to directly optimize multivariate performance measures. The resulting optimization problem can involve exponentially or infinitely many variables and constraints, which is more challenging than stan-dard structured output learning. To solve the StructHash optimization problem, we use a combination of column generation and cutting-plane techniques. We demonstrate the generality of StructHash by applying it to ranking prediction and image retrieval, and show that it outperforms a few state-of-the-art hashing methods.