http://hdl.handle.net/10027/8346 Thu, 20 Jun 2013 03:07:17 GMT 2013-06-20T03:07:17Z http://hdl.handle.net/10027/9640 How Likely Is Speciation in Neutral Ecology? Desjardins-Proulx, Philippe; Gravel, Dominique Patterns of biodiversity predicted by the neutral theory rely on a simple phenomenological model of speciation. To further investigate the effect of speciation on neutral biodiversity, we analyze a spatially explicit neutral model based on population genetics. We define the metacommunity as a system of populations exchanging migrants, and we use this framework to introduce speciation with little or no gene flow (allopatric and parapatric speciation). We find that with realistic mutation rates, our metacommunity model driven by neutral processes cannot support more than a few species. Adding natural selection in the population genetics of speciation increases the number of species in the metacommunity, but the level of diversity found in the Barro Colorado Island is difficult to reach. This is a copy of an article published in the American Naturalist © 2012 University of Chicago Press. The original version is available through University of Chicago Press at DOI: 10.1086/663196 Sun, 01 Jan 2012 06:00:00 GMT http://hdl.handle.net/10027/9640 2012-01-01T06:00:00Z http://hdl.handle.net/10027/8713 gMLC: a multi-label feature selection framework for graph classification Kong, Xiangnan; Yu, Philip S. Graph classification has been showing critical importance in a wide variety of applications, e.g. drug activity predictions and toxicology analysis. Current research on graph classification focuses on single-label settings. However, in many applications, each graph data can be assigned with a set of multiple labels simultaneously. Extract- ing good features using multiple labels of the graphs becomes an important step before graph classification. In this paper, we study the problem of multi-label feature selec- tion for graph classification and propose a novel solution, called gMLC, to efficiently search for optimal subgraph features for graph objects with multiple labels. Different from existing feature selection methods in vector spaces which assume the feature set is given, we perform multi-label feature selection for graph data in a progressive way together with the subgraph feature mining process. We derive an evaluation criterion to estimate the dependence between subgraph features and multiple labels of graphs. Then a branch-and-bound algorithm is proposed to efficiently search for optimal sub- graph features by judiciously pruning the subgraph search space using multiple labels. Empirical studies demonstrate that our feature selection approach can effectively boost multi-label graph classification performances and is more efficient by pruning the sub- graph search space using multiple labels. Post print version of article may differ from published version. The original publication is available at springerlink.com; DOI:10.1007/s10115-011-0407-3 Tue, 01 May 2012 05:00:00 GMT http://hdl.handle.net/10027/8713 2012-05-01T05:00:00Z