Jerry Scripps

Node roles and community structure in networks

A node role is a subjective characterization of the part it plays in a network structure. Knowing the role of a node is important for many link mining applications. For example, in Web search, nodes that are deemed to be authorities on a given topic are often found to be most relevant to the users queries. There are a number of metrics that can be used to assign roles to individual nodes in a network, including degree, closeness, and betweenness. None of these metrics, however, take into account the community structure that underlies the network. In this paper we define community-based roles that the nodes can assume (ambassadors, big fish, loners, and bridges) and show how existing link mining techniques can be improved by knowledge of such roles. A new community-based metric is introduced for estimating the number of communities linked to a node. Using this metric and a modification of degree, we show how to assign community-based roles to the nodes. We also illustrate the benefits of knowing the community-based node roles in the context of link-based classification and influence maximization.

Multistep-Ahead time series prediction

Multistep-ahead prediction is the task of predicting a sequence of values in a time series. A typical approach, known as multi-stage prediction, is to apply a predictive model step-by-step and use the predicted value of the current time step to determine its value in the next time step. This paper examines two alternative approaches known as independent value prediction and parameter prediction. The first approach builds a separate model for each prediction step using the values observed in the past. The second approach fits a parametric function to the time series and builds models to predict the parameters of the function. We perform a comparative study on the three approaches using multiple linear regression, recurrent neural networks, and a hybrid of hidden Markov model with multiple linear regression. The advantages and disadvantages of each approach are analyzed in terms of their error accumulation, smoothness of prediction, and learning difficulty.

Exploration of Link Structure and Community-Based Node Roles in Network Analysis

Communities are nodes in a network that are grouped together based on a common set of properties. While the communities and link structures are often thought to be in alignment, it may not be the case when the communities are defined using other external criterion. In this paper we provide a new way to measure the alignment. We also provide a new metric that can be used to estimate the number of communities to which a node is attached. This metric, along with degree, is used to assign a community-based role to nodes. We demonstrate the usefulness of the community-based node roles by applying them to the influence maximization problem.

Measuring the effects of preprocessing decisions and network forces in dynamic network analysis

Social networks have become a major focus of research in recent years, initially directed towards static networks but increasingly, towards dynamic ones. In this paper, we investigate how different pre-processing decisions and different network forces such as selection and influence affect the modeling of dynamic networks. We also present empirical justification for some of the modeling assumptions made in dynamic network analysis (e.g., first-order Markovian assumption) and develop metrics to measure the alignment between links and attributes under different strategies of using the historical network data. We also demonstrate the effect of attribute drift, that is, the importance of individual attributes in forming links change over time.

A matrix alignment approach for link prediction

This paper introduces a new discriminative learning technique for link prediction based on the matrix alignment approach. Our algorithm automatically determines the most predictive features of the link structure by aligning the adjacency matrix of a network with weighted similarity matrices computed from node attributes and neighborhood topological features. Experimental results on a variety of network data have demonstrated the effectiveness of this approach.

A Matrix Alignment Approach for Collective Classification

Within networks there is often a pattern to the way nodes link to one another. It has been shown that the accuracy of node classification can be improved by using the link data. One of the challenges to integrating the attribute and link data, though, is balancing the influence that each has on the classification decision. In this paper we present a matrix alignment approach to the problem of collective classification which weights the attributes and the links according to their predictive influence. The experiments show that while our approach provides comparable accuracy in prediction to other methods, it is also very fast and descriptive.

Exploring the Community Set Space

This paper presents the community set space canvas, a triangular canvas where the results of community finding algorithms can be plotted for comparison. The points of the triangle represent trivial sets, such as the set of one large community, and the edges are populated by well known set types, such as disjoint communities.

Link-Based Network Mining

Network mining is a growing area of research within the data mining community that uses metrics and algorithms from graph theory. In this chapter we present an overview of the different techniques in network mining and suggest future research possibilities in the direction of graph theory.

Link Mining for a Social Bookmarking Web Site

Social bookmarking tools enable users to save URLs for future reference, to create tags for annotating Web pages, and to share Web pages they found interesting with others. This paper presents a case study on the application of link mining to a social bookmarking Web site called del.icio.us. We investigated the user bookmarking and tagging behaviors and described several approaches to find surprising patterns in the data. We also identified the characteristics that made certain users more popular than others. Finally, we demonstrated the effectiveness of using social bookmarks and tags for predicting mutual ties between users.

Enumerating Communities for a Deeper Understanding of Community Finding

Often new insights and advancements are made by a detailed study of the problem and the solution space. The area of community finding has had many algorithms proposed recently, but to our knowledge there have not been any detailed studies of the solution space. In this paper, we present two algorithms for enumerating and unranking the possible valid community assignments for a network. To demonstrate the value of our algorithms, we also present some interesting insights gained by examining the solution space of some small networks.