Improving Fairness in Information Exposure by Adding Links

TL;DR

This paper explores how adding links to a network can make influence spreading more fair without explicitly optimizing for fairness, combining theoretical analysis with practical heuristics and experiments.

Contribution

It introduces a novel approach of modifying network structure to achieve fairness in influence spread, with theoretical hardness results and effective heuristics demonstrated experimentally.

Findings

Adding few edges can improve ex-post fairness significantly.

Heuristics outperform fairness-specific algorithms in practice.

Approach achieves fairness comparable to or better than existing methods.

Abstract

Fairness in influence maximization has been a very active research topic recently. Most works in this context study the question of how to find seeding strategies (deterministic or probabilistic) such that nodes or communities in the network get their fair share of coverage. Different fairness criteria have been used in this context. All these works assume that the entity that is spreading the information has an inherent interest in spreading the information fairly, otherwise why would they want to use the developed fair algorithms? This assumption may however be flawed in reality -- the spreading entity may be purely \emph{efficiency-oriented}. In this paper we propose to study two optimization problems with the goal to modify the network structure by adding links in such a way that efficiency-oriented information spreading becomes \emph{automatically fair}. We study the proposed optimization problems both from a theoretical and experimental perspective, that is, we give several hardness and hardness of approximation results, provide efficient algorithms for some special cases, and more importantly provide heuristics for solving one of the problems in practice. In our experimental study we then first compare the proposed heuristics against each other and establish the most successful one. In a second experiment, we then show that our approach can be very successful in practice. That is, we show that already after adding a few edges to the networks the greedy algorithm that purely maximizes spread surpasses all fairness-tailored algorithms in terms of ex-post fairness. Maybe surprisingly, we even show that our approach achieves ex-post fairness values that are comparable or even better than the ex-ante fairness values of the currently most efficient algorithms that optimize ex-ante fairness.