Accurately and efficiently estimating word similarities from text is fundamental in natural language processing.In this paper, we propose a fast and lightweight method for estimating similarities from streams by explicitly counting second-order co-occurrences.The method rests on the observation that words that are highly correlated with respect to such counts are also highly similar with respect to firstorder co-occurrences.Using buffers of cooccurred words per word to count secondorder co-occurrences, we can then estimate similarities in a single pass over data without having to do prohibitively expensive similarity calculations.We demonstrate that this approach is scalable, converges rapidly, behaves robustly under parameter changes, and that it captures word similarities on par with those given by state-of-the-art word embeddings.

Appropriately defining and then efficiently calculating similarities from large data sets are often essential in data mining, both for building tractable representations and for gaining understanding of data and generating processes. Here we rely on the premise that given a set of objects and their correlations, each object is characterized by its context, i.e. its correlations to the other objects, and that the similarity between two objects therefore can be expressed in terms of the similarity between their respective contexts. Resting on this principle, we propose a data-driven and highly scalable approach for discovering similarities from large data sets by representing objects and their relations as a correlation graph that is transformed to a similarity graph. Together these graphs can express rich structural properties among objects. Specifically, we show that concepts -- representations of abstract ideas and notions -- are constituted by groups of similar objects that can be identified by clustering the objects in the similarity graph. These principles and methods are applicable in a wide range of domains, and will here be demonstrated for three distinct types of objects: codons, artists and words, where the numbers of objects and correlations range from small to very large.

This paper presents a method for load balancing heterogeneous networks by dynamically assigning values to the LTE cell range expansion (CRE) parameter. The method records hand-over events online and adapts flexibly to changes in terminal traffic and mobility by maintaining statistical estimators that are used to support autonomous assignment decisions. The proposed approach has low overhead and is highly scalable due to a modularised and completely distributed design that exploits self-organisation based on local inter-cell interactions. An advanced simulator that incorporates terminal traffic patterns and mobility models with a radio access network simulator has been developed to validate and evaluate the method.

BACKGROUND: Codon substitution constitutes a fundamental process in molecular biology that has been studied extensively. However, prior studies rely on various assumptions, e.g. regarding the relevance of specific biochemical properties, or on conservation criteria for defining substitution groups. Ideally, one would instead like to analyze the substitution process in terms of raw dynamics, independently of underlying system specifics. In this paper we propose a method for doing this by identifying groups of codons and amino acids such that these groups imply closed dynamics. The approach relies on recently developed spectral and agglomerative techniques for identifying hierarchical organization in dynamical systems. RESULTS: We have applied the techniques on an empirically derived Markov model of the codon substitution process that is provided in the literature. Without system specific knowledge of the substitution process, the techniques manage to "blindly" identify multiple levels of dynamics; from amino acid substitutions (via the standard genetic code) to higher order dynamics on the level of amino acid groups. We hypothesize that the acquired groups reflect earlier versions of the genetic code. CONCLUSIONS: The results demonstrate the applicability of the techniques. Due to their generality, we believe that they can be used to coarse grain and identify hierarchical organization in a broad range of other biological systems and processes, such as protein interaction networks, genetic regulatory networks and food webs.

Current analyses of genomes from numerous species show that the diversity of their functional and behavioral characters is not proportional to the number of genes that encode the organism. We investigate the hypothesis that the diversity of organismal character is due to hierarchical organization. We do this with the recently introduced model of the finitary process soup, which allows for a detailed mathematical and quantitative analysis of the population dynamics of structural complexity. Here we show that global complexity in the finitary process soup is due to the emergence of successively higher levels of organization, that the hierarchical structure appears spontaneously, and that the process of structural innovation is facilitated by the discovery and maintenance of relatively noncomplex, but general, individuals in a population.