Transitive Identity Mapping Using Force-Based Clustering

摘要

In most information retrieval systems, software processes (whether agent-based or not) reason about passive items of data. An alternative approach instantiates each record as an agent that actively self-organizes with other agents (including queries). Imitating the movement of bodies under physical forces, we describe a distributed algorithm ("force-based clustering," or FBC) for dynamically clustering and querying large, heterogeneous, dynamic collections of entities. The algorithm moves entities in a virtual space in a way that estimates the transitive closure of the pairwise comparisons. We demonstrate this algorithm on a large, heterogeneous collection of records, each representing a person. We have some information about a person of interest, but no record in the collection directly matches this information. Application of FBC identifies a small subset of records that are good candidates for describing the person of interest, for further manual investigation and verification.