The paradigm adopted by classical Web search engines to output the results of a query is often inadequate. It typically consists of a ranked list of URLs, which may be very long and difficult to browse for the interested user. Recently, a lot of attention has been devoted to the design of Web meta-search clustering engines. These systems support the user by grouping the URLs returned by a search engine into distinct semantic categories, which are organized in a hierarchy; each category is properly labeled with a sentence that reflects its topics. However, even the most effective Web meta-search engines usually end-up by presenting many “meaningful ” categories together with a few “inexpressive ” categories on some specific queries. In this paper we describe a novel topology-driven approach to the design of a Web meta-search clustering engine. By this approach the set of URLs is modeled as a suitable graph and the hierarchy of categories is obtained by variants of classical graph-clustering algorithms. The topologydriven approach turns out to be comparable with traditional text-based strategies for the definition of the cluster hierarchy. In addition, our approach makes it natural to use graph visualization techniques to support the user in handling inexpressive labels. Namely, categories with inexpressive labels can be visually related to more meaningful ones. 1

Abstract. In this paper we define a type of cohesive subgroups – called communities – in hypergraphs, based on the edge connectivity of subhypergraphs. We describe a simple algorithm for the construction of these sets and show, based on examples from image segmentation and information retrieval, that these groups may be useful for the analysis and accessibility of large graphs and hypergraphs. 1

Common experience suggests that users of online services can be grouped into communities on the basis of interest. Much of the recent research on algorithms for identification of communities in the Web has focused on techniques that rely on link structures. In this paper, we describe a new technique for discovering communities of interest in Web services. Instead of relying upon link structures, we propose an algorithm based on user access behavior. A graph structure is created based on the user access patterns. This structure is shown to have useful properties for community discovery. We apply the algorithm to a synthetic dataset, known to show interest-based community structure, and use the results to compare our algorithm against other methodologies. We also apply the algorithm to two real world online services: a bookstore and an online radio. The case studies are relevant because they emphasize the contribution of the algorithm to find out communities in an environment without explicit structures that represent relationships among users.

In this paper we address the problem of topology discovery in unicast logical tree networks using endto-end measurements. Without any cooperation from the internal routers, topology estimation can be formulated as hierarchical clustering of the leaf nodes based on pair-wise correlations as similarity metrics. We investigate three types of similarity metrics: queueing delay measured by sandwich probes, delay variance measured by packet pairs, and loss rate measured also by packet pairs. Unlike previous work which first assumes the network topology is a binary tree and then tries to generalize to a non-binary tree, we provide a framework which directly deals with general logical tree topologies. Based on our proposed finite mixture model for the set of similarity measurements we develop a penalized hierarchical topology likelihood that leads to a natural clustering of the leaf nodes level by level. A hierarchical algorithm to estimate the topology is developed in a similar manner by finding the best partitions of the leaf nodes. Our simulations show that the algorithm is more robust than binary-tree based methods. The three types of similarity metrics are also evaluated under various network load conditions using ns-2. 1

Abstract—In this paper, we address the problem of topology discovery in unicast logical tree networks using end-to-end measurements. Without any cooperation from the internal routers, topology estimation can be formulated as hierarchical clustering of the leaf nodes based on pairwise correlations as similarity metrics. Unlike previous work that first assumes the network topology is a binary tree and then tries to generalize to a nonbinary tree, we provide a framework that directly deals with general logical tree topologies. A hierarchical algorithm to estimate the topology is developed in a recursive manner by finding the best partitions of the leaf nodes level by level. Our simulations show that the algorithm is more robust than binary-tree based methods. Index Terms—Graph-based clustering, mixture models, network tomography, topology estimation. I.