Fair Influence Maximization: A Welfare Optimization Approach

Rahmattalabi, Aida; Jabbari, Shahin; Lakkaraju, Himabindu; Vayanos, Phebe; Izenberg, Max; Brown, Ryan Andrew; Rice, Eric; Tambe, Milind

doi:10.48550/arxiv.2006.07906

Cited by 4 publications

(4 citation statements)

References 25 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We proceed by reviewing more distant works that still treat fairness issues in influence maximization. Rahmattalabi et al (2020) further extend the group-fairness approach of Tsang et al (2019) by following a different path. From the expected fraction of vertices reached in each community, the authors define a utility vector over the entire population of vertices, and then take a welfare optimization approach by optimizing a decision criterion which is a function of this utility vector.…”

Section: Further Related Workmentioning

confidence: 99%

“…Another line of research has investigated the fairness of the diffusion process with respect to the vertices, i.e., the users in the network. Indeed when only efficiency is being optimized, some users, or communities, i.e., groups of users, might get an unfairly low coverage (Ali et al, 2019;Fish et al, 2019;Farnadi et al, 2020;Khajehnejad et al, 2020;Rahmattalabi et al, 2020;Stoica et al, 2020;Tsang et al, 2019). An intuitive criterion to consider here is the maximin criterion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fairness in Influence Maximization through Randomization

Becker¹,

D’Angelo²,

Ghobadi³

et al. 2022

jair

View full text Add to dashboard Cite

The influence maximization paradigm has been used by researchers in various fields in order to study how information spreads in social networks. While previously the attention was mostly on efficiency, more recently fairness issues have been taken into account in this scope. In the present paper, we propose to use randomization as a mean for achieving fairness. While this general idea is not new, it has not been applied in this area. Similar to previous works like Fish et al. (WWW ’19) and Tsang et al. (IJCAI ’19), we study the maximin criterion for (group) fairness. In contrast to their work however, we model the problem in such a way that, when choosing the seed sets, probabilistic strategies are possible rather than only deterministic ones. We introduce two different variants of this probabilistic problem, one that entails probabilistic strategies over nodes (node-based problem) and a second one that entails probabilistic strategies over sets of nodes (set-based problem). After analyzing the relation between the two probabilistic problems, we show that, while the original deterministic maximin problem was inapproximable, both probabilistic variants permit approximation algorithms that achieve a constant multiplicative factor of 1 − 1/e minus an additive arbitrarily small error that is due to the simulation of the information spread. For the node-based problem, the approximation is achieved by observing that a polynomial-sized linear program approximates the problem well. For the set-based problem, we show that a multiplicative-weight routine can yield the approximation result. For an experimental study, we provide implementations of multiplicative-weight routines for both the set-based and the node-based problems and compare the achieved fairness values to existing methods. Maybe non-surprisingly, we show that the ex-ante values, i.e., minimum expected value of an individual (or group) to obtain the information, of the computed probabilistic strategies are significantly larger than the (ex-post) fairness values of previous methods. This indicates that studying fairness via randomization is a worthwhile path to follow. Interestingly and maybe more surprisingly, we observe that even the ex-post fairness values, i.e., fairness values of sets sampled according to the probabilistic strategies computed by our routines, dominate over the fairness achieved by previous methods on many of the instances tested.

show abstract

Section: Further Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fairness in Influence Maximization through Randomization

Becker¹,

D’Angelo²,

Ghobadi³

et al. 2022

jair

View full text Add to dashboard Cite

show abstract

“…Another line of research has investigated the fairness of the diffusion process with respect to the vertices, i.e., the users in the network. Indeed when only efficiency is being optimized, some users, or communities, i.e., groups of users, might get an unfairly low coverage (Ali et al 2019;Fish et al 2019;Farnad, Babaki, and Gendreau 2020;Khajehnejad et al 2020;Rahmattalabi et al 2020;Stoica, Han, and Chaintreau 2020;Tsang et al 2019). A intuitive criterion to consider here is the maximin criterion.…”

Section: Introductionmentioning

confidence: 99%

Fairness in Influence Maximization through Randomization

Becker

D’Angelo

Ghobadi

et al. 2021

AAAI

View full text Add to dashboard Cite

The influence maximization paradigm has been used by researchers in various fields in order to study how information spreads in social networks. While previously the attention was mostly on efficiency, more recently fairness issues have been taken into account in this scope. In the present paper, we propose to use randomization as a mean for achieving fairness. While this general idea is not new, it has not been applied in the area of information spread in networks. Similar to previous works like Fish et al. (WWW '19) and Tsang et al. (IJCAI '19), we study the maximin criterion for (group) fairness. By allowing randomized solutions, we introduce two different variants of this problem. While the original deterministic maximin problem has been shown to be inapproximable, interestingly, we show that both probabilistic variants permit approximation algorithms with a constant multiplicative factor of 1-1/e plus an additive arbitrarily small error that is due to the simulation of the information spread. For an experimental study, we provide implementations of our methods and compare the achieved fairness values to existing methods. Non-surprisingly, the ex-ante values, i.e., minimum expected value of an individual (or group) to obtain the information, of the computed probabilistic strategies are significantly larger than the (ex-post) fairness values of previous methods. This confirms that studying fairness via randomization is a worthwhile direction. More surprisingly, we observe that even the ex-post fairness values, i.e., fairness values of sets sampled according to the probabilistic strategies, computed by our routines dominate over the fairness achieved by previous methods on most of the instances tested.

show abstract

“…In-processing methods modify the optimization procedure of the classifier to integrate fairness criteria in the objective function [45,3,12]. This is often done by using a regularization term [24,74,75,76,32,6,7,61,43], meta-learning algorithms [15], reduction-based methods [2,22], or adversarial training [54,78,16,72]. Postprocessing methods adjust the output of the AI algorithm to enhance fairness in decisions [29].…”

Section: Introduction and Related Workmentioning

confidence: 99%

Fairness-aware Summarization for Justified Decision-Making

Keymanesh¹,

Berger-Wolf²,

Elsner³

et al. 2021

Preprint

View full text Add to dashboard Cite

In many applications such as recidivism prediction, facility inspection, and benefit assignment, it's important for individuals to know the decision-relevant information for the model's prediction. In addition, the model's predictions should be fairly justified. Essentially, decision-relevant features should provide sufficient information for the predicted outcome and should be independent of the membership of individuals in protected groups such as race and gender. In this work, we focus on the problem of (un)fairness in the justification of the text-based neural models. We tie the explanatory power of the model to fairness in the outcome and propose a fairness-aware summarization mechanism to detect and counteract the bias in such models. Given a potentially biased natural language explanation for a decision, we use a multi-task neural model and an attribution mechanism based on integrated gradients to extract the high-utility and discrimination-free justifications in the form of a summary. The extracted summary is then used for training a model to make decisions for individuals. Results on several real world datasets suggests that our method: (i) assists users to understand what information is used for the model's decision and (ii) enhances the fairness in outcomes while significantly reducing the demographic leakage.

show abstract

Fair Influence Maximization: A Welfare Optimization Approach

Cited by 4 publications

References 25 publications

Fairness in Influence Maximization through Randomization

Fairness in Influence Maximization through Randomization

Fairness in Influence Maximization through Randomization

Fairness-aware Summarization for Justified Decision-Making

Contact Info

Product

Resources

About