arXiv subjects

Gianlorenzo D'Angelo

Publications and source records attributed to Gianlorenzo D'Angelo.

29 records · Page 2Linked to original sources

arXiv2020

Multi-Winner Election Control via Social Influence

In an election, we are given a set of voters, each having a preference list over a set of candidates, that are distributed on a social network. We consider a scenario where voters may change their preference lists as a consequence of the messages received by their neighbors in a social network. Specifically, we consider a political campaign that spreads messages in a social network in support or against a given candidate and the spreading follows a dynamic model for information diffusion. When a message reaches a voter, this latter changes its preference list according to an update rule. The election control problem asks to find a bounded set of nodes to be the starter of a political campaign in support (constructive problem) or against (destructive problem) a given target candidate $c$, in such a way that the margin of victory of $c$ w.r.t. its most voted opponents is maximized. It has been shown that several variants of the problem can be solved within a constant factor approximation of the optimum, which shows that controlling elections by means of social networks is doable and constitutes a real problem for modern democracies. Most of the literature, however, focuses on the case of single-winner elections. In this paper, we define the election control problem in social networks for "multi-winner elections" with the aim of modeling parliamentarian elections. Differently from the single-winner case, we show that the multi-winner election control problem is NP-hard to approximate within any factor in both constructive and destructive cases. We then study a relaxation of the problem where votes are aggregated on the basis of parties (instead of single candidates), which is a variation of the so-called "straight-party voting" used in some real parliamentarian elections. We show that the latter problem remains NP-hard but can be approximated within a constant factor.

cs.SI↗

arXiv2020

Maximizing Influence-based Group Shapley Centrality

One key problem in network analysis is the so-called influence maximization problem, which consists in finding a set $S$ of at most $k$ seed users, in a social network, maximizing the spread of information from $S$. This paper studies a related but slightly different problem: We want to find a set $S$ of at most $k$ seed users that maximizes the spread of information, when $S$ is added to an already pre-existing - but unknown - set of seed users $T$. We consider such scenario to be very realistic. Assume a central entity wants to spread a piece of news, while having a budget to influence $k$ users. This central authority may know that some users are already aware of the information and are going to spread it anyhow. The identity of these users being however completely unknown. We model this optimization problem using the Group Shapley value, a well-founded concept from cooperative game theory. While the standard influence maximization problem is easy to approximate within a factor $1-1/e-ε$ for any $ε>0$, assuming common computational complexity conjectures, we obtain strong hardness of approximation results for the problem at hand in this paper. Maybe most prominently, we show that it cannot be approximated within $1/n^{o(1)}$ under the Gap Exponential Time Hypothesis. Hence, it is unlikely to achieve anything better than a polynomial factor approximation. Nevertheless, we show that a greedy algorithm can achieve a factor of $\frac{1-1/e}{k}-ε$ for any $ε>0$, showing that not all is lost in settings where $k$ is bounded.

cs.GT↗

arXiv2019

Exploiting Social Influence to Control Elections Based on Scoring Rules

Online social networks are used to diffuse opinions and ideas among users, enabling a faster communication and a wider audience. The way in which opinions are conditioned by social interactions is usually called social influence. Social influence is extensively used during political campaigns to advertise and support candidates. Herein we consider the problem of exploiting social influence in a network of voters in order to change their opinion about a target candidate with the aim of increasing his chance to win/lose the election in a wide range of voting systems. We introduce the Linear Threshold Ranking, a natural and powerful extension of the well-established Linear Threshold Model, which describes the change of opinions taking into account the amount of exercised influence. We are able to maximize the score of a target candidate up to a factor of $1-1/e$ by showing submodularity. We exploit such property to provide a $\frac{1}{3}(1-1/e)$-approximation algorithm for the constructive election control problem. Similarly, we get a $\frac{1}{2}(1-1/e)$-approximation ratio in the destructive scenario. The algorithm can be used in arbitrary scoring rule voting systems, including plurality rule and borda count. Finally, we perform an experimental study on real-world networks, measuring Probability of Victory (PoV) and Margin of Victory (MoV) of the target candidate, to validate the model and to test the capability of the algorithm.

cs.SI↗

arXiv2019

Balancing spreads of influence in a social network

The personalization of our news consumption on social media has a tendency to reinforce our pre-existing beliefs instead of balancing our opinions. This finding is a concern for the health of our democracies which rely on an access to information providing diverse viewpoints. To tackle this issue from a computational perspective, Garimella et al. (NIPS'17) modeled the spread of these viewpoints, also called campaigns, using the well-known independent cascade model and studied an optimization problem that aims at balancing information exposure in a social network when two opposing campaigns propagate in the network. The objective in their $NP$-hard optimization problem is to maximize the number of people that are exposed to either both or none of the viewpoints. For two different settings, one corresponding to a model where campaigns spread in a correlated manner, and a second one, where the two campaigns spread in a heterogeneous manner, they provide constant ratio approximation algorithms. In this paper, we investigate a more general formulation of this problem. That is, we assume that $μ$ different campaigns propagate in a social network and we aim to maximize the number of people that are exposed to either $ν$ or none of the campaigns, where $μ\geν\ge2$. We provide dedicated approximation algorithms for both the correlated and heterogeneous settings. Interestingly, for the heterogeneous setting with $ν\ge 3$, we give a reduction leading to several approximation hardness results. Maybe most importantly, we obtain that the problem cannot be approximated within a factor of $n^{-g(n)}$ for any $g(n)=o(1)$ assuming Gap-ETH, denoting with $n$ the number of nodes in the social network. For $ν\ge 4$, there is no $n^{-ε}$-approximation algorithm if a certain class of one-way functions exists, where $ε> 0$ is a given constant which depends on $ν$.

cs.SI↗

arXiv2019

On the fixed-parameter tractability of the maximum connectivity improvement problem

In the Maximum Connectivity Improvement (MCI) problem, we are given a directed graph $G=(V,E)$ and an integer $B$ and we are asked to find $B$ new edges to be added to $G$ in order to maximize the number of connected pairs of vertices in the resulting graph. The MCI problem has been studied from the approximation point of view. In this paper, we approach it from the parameterized complexity perspective in the case of directed acyclic graphs. We show several hardness and algorithmic results with respect to different natural parameters. Our main result is that the problem is $W[2]$-hard for parameter $B$ and it is FPT for parameters $|V| - B$ and $ν$, the matching number of $G$. We further characterize the MCI problem with respect to other complementary parameters.

cs.DM↗

arXiv2018

Coverage Centrality Maximization in Undirected Networks

Centrality metrics are among the main tools in social network analysis. Being central for a user of a network leads to several benefits to the user: central users are highly influential and play key roles within the network. Therefore, the optimization problem of increasing the centrality of a network user recently received considerable attention. Given a network and a target user $v$, the centrality maximization problem consists in creating $k$ new links incident to $v$ in such a way that the centrality of $v$ is maximized, according to some centrality metric. Most of the algorithms proposed in the literature are based on showing that a given centrality metric is monotone and submodular with respect to link addition. However, this property does not hold for several shortest-path based centrality metrics if the links are undirected. In this paper we study the centrality maximization problem in undirected networks for one of the most important shortest-path based centrality measures, the coverage centrality. We provide several hardness and approximation results. We first show that the problem cannot be approximated within a factor greater than $1-1/e$, unless $P=NP$, and, under the stronger gap-ETH hypothesis, the problem cannot be approximated within a factor better than $1/n^{o(1)}$, where $n$ is the number of users. We then propose two greedy approximation algorithms, and show that, by suitably combining them, we can guarantee an approximation factor of $Ω(1/\sqrt{n})$. We experimentally compare the solutions provided by our approximation algorithm with optimal solutions computed by means of an exact IP formulation. We show that our algorithm produces solutions that are very close to the optimum.

cs.DS↗

arXiv2018

Generalized budgeted submodular set function maximization

In this paper we consider a generalization of the well-known budgeted maximum coverage problem. We are given a ground set of elements and a set of bins. The goal is to find a subset of elements along with an associated set of bins, such that the overall cost is at most a given budget, and the profit is maximized. Each bin has its own cost and the cost of each element depends on its associated bin. The profit is measured by a monotone submodular function over the elements. We first present an algorithm that guarantees an approximation factor of $\frac{1}{2}\left(1-\frac{1}{e^α}\right)$, where $α\leq 1$ is the approximation factor of an algorithm for a sub-problem. We give two polynomial-time algorithms to solve this sub-problem. The first one gives us $α=1- ε$ if the costs satisfies a specific condition, which is fulfilled in several relevant cases, including the unitary costs case and the problem of maximizing a monotone submodular function under a knapsack constraint. The second one guarantees $α=1-\frac{1}{e}-ε$ for the general case. The gap between our approximation guarantees and the known inapproximability bounds is $\frac{1}{2}$. We extend our algorithm to a bi-criterion approximation algorithm in which we are allowed to spend an extra budget up to a factor $β\geq 1$ to guarantee a $\frac{1}{2}\left(1-\frac{1}{e^{αβ}}\right)$-approximation. If we set $β=\frac{1}α\ln \left(\frac{1}{2ε}\right)$, the algorithm achieves an approximation factor of $\frac{1}{2}-ε$, for any arbitrarily small $ε>0$.

cs.DS↗

arXiv2018

Improving the betweenness centrality of a node by adding links

Betweenness is a well-known centrality measure that ranks the nodes according to their participation in the shortest paths of a network. In several scenarios, having a high betweenness can have a positive impact on the node itself. Hence, in this paper we consider the problem of determining how much a vertex can increase its centrality by creating a limited amount of new edges incident to it. In particular, we study the problem of maximizing the betweenness score of a given node -- Maximum Betweenness Improvement (MBI) -- and that of maximizing the ranking of a given node -- Maximum Ranking Improvement (MRI). We show that MBI cannot be approximated in polynomial-time within a factor $(1-\frac{1}{2e})$ and that MRI does not admit any polynomial-time constant factor approximation algorithm, both unless $P=NP$. We then propose a simple greedy approximation algorithm for MBI with an almost tight approximation ratio and we test its performance on several real-world networks. We experimentally show that our algorithm highly increases both the betweenness score and the ranking of a given node ant that it outperforms several competitive baselines. To speed up the computation of our greedy algorithm, we also propose a new dynamic algorithm for updating the betweenness of one node after an edge insertion, which might be of independent interest. Using the dynamic algorithm, we are now able to compute an approximation of MBI on networks with up to $10^5$ edges in most cases in a matter of seconds or a few minutes.

cs.DS↗

arXiv2017

Selecting nodes and buying links to maximize the information diffusion in a network

The Independent Cascade Model (ICM) is a widely studied model that aims to capture the dynamics of the information diffusion in social networks and in general complex networks. In this model, we can distinguish between active nodes which spread the information and inactive ones. The process starts from a set of initially active nodes called seeds. Recursively, currently active nodes can activate their neighbours according to a probability distribution on the set of edges. After a certain number of these recursive cycles, a large number of nodes might become active. The process terminates when no further node gets activated. Starting from the work of Domingos and Richardson, several studies have been conducted with the aim of shaping a given diffusion process so as to maximize the number of activated nodes at the end of the process. One of the most studied problems has been formalized by Kempe et al. and consists in finding a set of initial seeds that maximizes the expected number of active nodes under a budget constraint. In this paper we study a generalization of the problem of Kempe et al. in which we are allowed to spend part of the budget to create new edges incident to the seeds. That is, the budget can be spent to buy seeds or edges according to a cost function. The problem does not admin a PTAS, unless $P=NP$. We propose two approximation algorithms: the former one gives an approximation ratio that depends on the edge costs and increases when these costs are high; the latter algorithm gives a constant approximation guarantee which is greater than that of the first algorithm when the edge costs can be small.

cs.DS↗

arXiv2017

Recommending links through influence maximization

The link recommendation problem consists in suggesting a set of links to the users of a social network in order to increase their social circles and the connectivity of the network. Link recommendation is extensively studied in the context of social networks and of general complex networks due to its wide range of applications. Most of the existing link recommendation methods estimate the likelihood that a link is adopted by users and recommend links that are likely to be established. However, most of such methods overlook the impact that the suggested links have on the capability of the network to spread information. Indeed, such capability is directly correlated with both the engagement of a single user and the revenue of online social networks. In this paper, we study link recommendation systems from the point of view of information diffusion. In detail, we consider the problem in which we are allowed to spend a given budget to create new links so to suggest a bounded number of possible persons to whom become friend in order to maximize the influence of a given set of nodes. We model the influence diffusion in a network with the popular Independent Cascade model.

cs.DS↗

arXiv2016

Local Distributed Verification

In the framework of distributed network computing, it is known that, for every network predicate, each network configuration that satisfies this predicate can be proved using distributed certificates which can be verified locally. However, this requires to leak information about the identities of the nodes in the certificates, which might not be applicable in a context in which privacy is desirable. Unfortunately, it is known that if one insists on certificates independent of the node identities, then not all network predicates can be proved using distributed certificates that can be verified locally. In this paper, we prove that, for every network predicate, there is a distributed protocol satisfying the following two properties: (1) for every network configuration that is legal w.r.t. the predicate, and for any attempt by an adversary to prove the illegality of that configuration using distributed certificates, there is a locally verifiable proof that the adversary is wrong, also using distributed certificates; (2) for every network configuration that is illegal w.r.t. the predicate, there is a proof of that illegality, using distributed certificates, such that no matter the way an adversary assigns its own set of distributed certificates in an attempt to prove the legality of the configuration, the actual illegality of the configuration will be locally detected. In both cases, the certificates are independent of the identities of the nodes. These results are achieved by investigating the so-called local hierarchy of complexity classes in which the certificates do not exploit the node identities. Indeed, we give a characterization of such a hierarchy, which is of its own interest

cs.DC↗