Abstract </head> <body text="#000000" bgcolor="#FFFFFF" link="#0000EF" vlink="#CF30CF" alink="#FF0000" nosave> <br> <center><h2> Inferring Dynamically Evolving Networks </h2> <br> <h2> Eric Xing </h2> <h3> (Carnegie Mellon University) </h3> </center> <br> Networks are a fundamental form of representation of information. In many problems arising in biology, social sciences and various other fields, it is often necessary to analyze populations of entities such as molecules or individuals, interconnected by a network of relationships. While there is a rich literature on modeling a static network at a single point in time, or time-invariant networks, much less has been done toward modeling the dynamical processes underlying networks that are rewiring over time; and on developing learning techniques for recovering unobserved networks, especially in a dynamic context, and for large-scale networks. We present a latent dynamic exponential random graph model for reverse engineering temporally rewiring networks from time series of node attributes such as activities of social actors or expression levels of genes. Although at each time only a single sample of the node attributes is observed, under our model an MCMC sample algorithm can be applied to infer the latent time-specific topologies of the evolving networks conditioning on the observed time series data. We present empirical results on both a synthetic data set and a Drosophila lifecycle gene expression data set. Our approach represents an initial foray into an in-depth investigation of the mechanisms and processes of network generation and rewiring in complex systems in social and biology problems. <br><br><br> <a href="index.html">Back to main page</a><br><br> <hr> <p><br><br>  <script type="text/javascript"> var sc_project=2800657; var sc_invisible=0; var sc_partition=28; var sc_security="dd1187b0"; </script> <script type="text/javascript" src="http://www.statcounter.com/counter/counter_xhtml.js"></script><noscript><div class="statcounter"><a class="statcounter" href="http://www.statcounter.com/"><img class="statcounter" src="http://c29.statcounter.com/2800657/0/dd1187b0/0/" alt="free stats" /></a></div></noscript>  </body> </html>