Fuzzy lattice reasoning (FLR) type neural computation for weighted graph partitioning

摘要

The fuzzy lattice reasoning (FLR) neural network was introduced lately based on an inclusion measure function. This work presents a novel FLR extension, namely agglomerative similarity measure FLR, or asmFLR for short, for clustering based on a similarity measure function, the latter (function) may also be based on a metric. We demonstrate application in a metric space emerging from a weighted graph towards partitioning it. The asmFLR compares favorably with four alternative graph-clustering algorithms from the literature in a series of computational experiments on artificial data. In addition, our work introduces a novel index for the quality of clustering, which (index) compares favorably with two popular indices from the literature.