Hamming DHT: Taming the similarity search

The semantic meaning of a content is frequently represented by content vectors in which each dimension represents an attribute of this content, such as, keywords in a text, colors in a picture or profile information in a social network. However, one important challenge in this semantic context is the storage and retrieval of similar contents, such as the search for similar images assisting a medical procedure. Based on it, this paper presents a new Distributed Hash Table (DHT), called Hamming DHT, in which Locality Sensitive Hashing (LSH) functions, specially the Random Hyperplane Hashing (RHH), are used to generate content identifiers, propitiating a scenario in which similar contents are stored in peers nearly located in the indexing space of the proposed DHT. The evaluations of this work simulate profiles in a social network to verify if the proposed DHT is capable of reducing the number of hops required in order to improve the recall in the context of a similarity search.