Social networks involve both positive and negative relationships, which can be captured in signed graphs. The _edge sign prediction problem_ aims to predict whether an interaction between a pair of nodes will be positive or negative. We provide theoretical results for this problem that motivate natural improvements to recent heuristics. The edge sign prediction problem is related to correlation clustering; a positive relationship means being in the same cluster. We consider the following model for two clusters: we are allowed to query any pair of nodes whether they belong to the same cluster or not, but the answer to the query is corrupted with some probability $0<q<\frac{1}{2}$. Let $\delta=1-2q$ be the bias. We provide an algorithm that recovers all signs correctly with high probability in the presence of noise with $O(\frac{n\log n}{\delta^2}+\frac{\log^2 n}{\delta^6})$ queries. This is the best known result for this problem for all but tiny $\delta$, improving on the recent work of Mazumdar and Saha. We also provide an algorithm that performs $O(\frac{n\log n}{\delta^4})$ queries, and uses breadth first search as its main algorithmic primitive. While both the running time and the number of queries for this algorithm are sub-optimal, our result relies on novel theoretical techniques, and naturally suggests the use of edge-disjoint paths as a feature for predicting signs in online social networks. Correspondingly, we experiment with using edge disjoint $s-t$ paths of short length as a feature for predicting the sign of edge $(s,t)$ in real-world signed networks. Empirical findings suggest that the use of such paths improves the classification accuracy, especially for pairs of nodes with no common neighbors.

In this work we consider the problem of recovering $n$ discrete random variables $x_i\in \{0,\ldots,k-1\}, 1 \leq i \leq n$ (where $k$ is constant) with the smallest possible number of queries to a noisy oracle that returns for a given query pair $(x_i,x_j)$ a noisy measurement of their modulo $k$ pairwise difference, i.e., $y_{ij} = (x_i-x_j) \mod k$. This is a joint discrete alignment problem with important applications in computer vision, graph mining, and spectroscopy imaging. Our main result is a polynomial time algorithm that learns exactly with high probability the alignment (up to some unrecoverable offset) using $O(n^{1+o(1)})$ queries.

Star sampling (SS) is a random sampling procedure on a graph wherein each sample consists of a randomly selected vertex (the star center) and its (one-hop) neighbors (the star points). We consider the use of SS to find any member of a target set of vertices in a graph, where the figure of merit (cost) is either the expected number of samples (unit cost) or the expected number of star centers plus star points (linear cost) until a vertex in the target set is encountered, either as a star center or as a star point. We analyze these two performance measures on three related star sampling paradigms: SS with replacement (SSR), SS without center replacement (SSC), and SS without star replacement (SSS). Exact and approximate expressions are derived for the expected unit and linear costs of SSR, SSC, and SSS on Erdős-Rényi (ER) random graphs. The approximations are seen to be accurate. SSC/SSS are notably better than SSR under unit cost for low-density ER graphs, while SSS is notably better than SSR/SSC under linear cost for low- to moderate-density ER graphs. Simulations on twelve "real-world" graphs shows the cost approximations to be of variable quality: the SSR and SSC approximations are uniformly accurate, while the SSS approximation, derived for an ER graph, is of variable accuracy.

The goal of is to study how increased variability in the degree distribution impacts the global connectivity properties of a large network. We approach this question by modeling the network as a uniform random graph with a given degree sequence. We analyze the effect of the degree variability on the approximate size of the largest connected component using stochastic ordering techniques. A counterexample shows that a higher degree variability may lead to a larger connected component, contrary to basic intuition about branching processes. When certain extremal cases are ruled out, the higher degree variability is shown to decrease the limiting approximate size of the largest connected component.

We study the use of random walks as an efficient estimator of global properties of large undirected graphs, for example the number of edges, vertices, triangles, and generally, the number of small fixed subgraphs. We consider two methods based on first returns of random walks: the cycle formula of regenerative processes and weighted random walks with edge weights defined by the property under investigation. We review the theoretical foundations for these methods, and indicate how they can be adapted for the general non-intrusive investigation of large online networks.

Over the last decade we have witnessed the rapid proliferation of online networks and Internet activity. Although such activity is generally considered a blessing, it also brings with it a large increase in risk of computer malware—malignant software that actively spreads from one computer to another. To date, the majority of existing models of malware spread use stochastic behavior, when the set of neighbors infected from the current set of infected nodes is chosen obliviously. In this work, we initiate the study of _planned_-infection strategies that can decide intelligently which neighbors of infected nodes to infect next in order to maximize their spread, while maintaining a “signature” similar to the oblivious stochastic infection strategy in order not to be discovered. We first establish that computing optimal and near-optimal planned strategies is computationally hard. We then identify necessary and sufficient conditions in terms of network structure and edge infection probabilities such that the planned process can infect polynomially more nodes than the stochastic process while maintaining a similar “signature” as the oblivious stochastic infection strategy. Among our results is a surprising connection between an additional structural quantity of interest in a network, the network _toughness_, and planned infections. Based on the network toughness, we characterize networks where existence of planned strategies that are pandemic (infect all nodes) is guaranteed, as well as efficiently computable.

We give a clustering algorithm for connection graphs, that is, weighted graphs in which each edge is associated with a _d_-dimensional rotation. The problem of interest is to identify subsets of small Cheeger ratio that have a high level of consistency, i.e., that have a small edge boundary and for which the rotations along any distinct paths joining two vertices are the same or within some small error factor. We use PageRank vectors as well as tools related to the Cheeger constant to give a clustering algorithm that runs in nearly linear time.

We consider stochastic transition matrices from large social and information networks. For these matrices, we describe and evaluate three fast methods to estimate one column of the matrix exponential. The methods are designed to exploit the properties inherent in social networks, such as a power-law degree distribution. Using only this property, we prove that one of our three algorithms has a sublinear runtime. We present further experimental evidence showing that all three of them run quickly on social networks with billions of edges, and they accurately identify the largest elements of the column.

**Abstract** Many networks, including the Internet, social networks, and biological relations, are found to be naturally divided into communities of densely connected nodes, known as community structure. Since Newman's suggestion of using _modularity_ as a measure to qualify the goodness of community structures, many efficient methods to maximize modularity have been proposed but without _optimality guarantees_. In this work we study exact and theoretically near-optimal algorithms for maximizing modularity. In the first part, we investigate the complexity and approximability of the problem on tree graphs. Somewhat surprisingly, the problem is still NP-complete on trees. We then provide a polynomial time algorithm for uniform-weighted trees and a pseudopolynomial time algorithm and a PTAS for trees with arbitrary weights. In the second part, we present a family of compact linear programming formulations for the problem in general graphs. These formulations exploit the graph connectivity structure and reduce substantially the number of constraints, thus, they vastly improve the running time for solving linear programming and integer programming. As a result, networks of thousands of vertices can be solved in minutes, whereas the current largest instance solved with mathematical programming has fewer than 250 vertices.

Many problems arising in dealing with high-dimensional data sets involve connection graphs in which each edge is associated with both an edge weight and a _d_-dimensional linear transformation. We consider vectorized versions of PageRank and effective resistance that can be used as basic tools for organizing and analyzing complex data sets. For example, generalized PageRank and effective resistance can be utilized to derive and modify diffusion distances for vector diffusion maps in data and image processing. Furthermore, the edge-ranking of the connection graphs determined by vectorized PageRank and effective resistance are an essential part of sparsification algorithms that simplify and preserve the global structure of connection graphs. In addition, we examine consistencies in a connection graph, particularly in the applications of recovering low-dimensional data sets and the reduction of noise. In these applications, we analyze the effect of deleting edges with high edge rank.