Adversarial Graph Embeddings for Fair Influence Maximization over Social
Networks
- URL: http://arxiv.org/abs/2005.04074v2
- Date: Mon, 11 May 2020 01:01:31 GMT
- Title: Adversarial Graph Embeddings for Fair Influence Maximization over Social
Networks
- Authors: Moein Khajehnejad, Ahmad Asgharian Rezaei, Mahmoudreza Babaei, Jessica
Hoffmann, Mahdi Jalili and Adrian Weller
- Abstract summary: We introduce Adversarial Graphdings: we co-train an auto-encoder for embedding and a discriminator to discern sensitive attributes.
We then find a good initial set by clustering the embeddings.
While there are typically trade-offs between fairness and influence objectives, our experiments on synthetic and real-world datasets show that our approach dramatically reduces disparity.
- Score: 32.795094910922614
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Influence maximization is a widely studied topic in network science, where
the aim is to reach the maximum possible number of nodes, while only targeting
a small initial set of individuals. It has critical applications in many
fields, including viral marketing, information propagation, news dissemination,
and vaccinations. However, the objective does not usually take into account
whether the final set of influenced nodes is fair with respect to sensitive
attributes, such as race or gender. Here we address fair influence
maximization, aiming to reach minorities more equitably. We introduce
Adversarial Graph Embeddings: we co-train an auto-encoder for graph embedding
and a discriminator to discern sensitive attributes. This leads to embeddings
which are similarly distributed across sensitive attributes. We then find a
good initial set by clustering the embeddings. We believe we are the first to
use embeddings for the task of fair influence maximization. While there are
typically trade-offs between fairness and influence maximization objectives,
our experiments on synthetic and real-world datasets show that our approach
dramatically reduces disparity while remaining competitive with
state-of-the-art influence maximization methods.
Related papers
- Influence Maximization via Graph Neural Bandits [54.45552721334886]
We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced.
We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced.
arXiv Detail & Related papers (2024-06-18T17:54:33Z) - Detecting and Mitigating Bias in Algorithms Used to Disseminate Information in Social Networks [0.03883607294385062]
Social connections are a conduit through which individuals communicate, information propagates, and diseases spread.
Identifying individuals that are more likely to adopt ideas or technologies and spread them to others is essential in order to develop effective information campaigns, fight epidemics, and to maximize the reach of limited resources.
Here we show that seeding information using influence methods only benefits connected and central individuals, consistently leaving the most vulnerable behind.
Our work demonstrates how to find fairer influencer sets, highlighting that in our search for maximizing information, we do not need to compromise on information equality.
arXiv Detail & Related papers (2024-05-21T13:17:57Z) - MAPPING: Debiasing Graph Neural Networks for Fair Node Classification
with Limited Sensitive Information Leakage [1.8238848494579714]
We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification.
Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
arXiv Detail & Related papers (2024-01-23T14:59:46Z) - Influence Maximization with Unknown Individual Effect on General Network [3.4049427793086324]
The identification of a seed set to maximize information spread in a network is crucial, a concept known as Influence Maximization (IM)
IM algorithms could naturally extend to cases where each node is equipped with specific weight, referred to as individual effect, to measure the node's importance.
In our paper, we address this through the development of a Causal Influence Maximization (CauIM) algorithm.
arXiv Detail & Related papers (2023-01-28T15:34:03Z) - Contextual Bandits for Advertising Campaigns: A Diffusion-Model
Independent Approach (Extended Version) [73.59962178534361]
We study an influence problem in which little is assumed to be known about the diffusion network or about the model that determines how information may propagate.
In this setting, an explore-exploit approach could be used to learn the key underlying diffusion parameters, while running the campaign.
We describe and compare two methods of contextual multi-armed bandits, with upper-confidence bounds on the remaining potential of influencers.
arXiv Detail & Related papers (2022-01-13T22:06:10Z) - Learning Fair Node Representations with Graph Counterfactual Fairness [56.32231787113689]
We propose graph counterfactual fairness, which considers the biases led by the above facts.
We generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.
Our framework outperforms the state-of-the-art baselines in graph counterfactual fairness.
arXiv Detail & Related papers (2022-01-10T21:43:44Z) - Unbiased Graph Embedding with Biased Graph Observations [52.82841737832561]
We propose a principled new way for obtaining unbiased representations by learning from an underlying bias-free graph.
Based on this new perspective, we propose two complementary methods for uncovering such an underlying graph.
arXiv Detail & Related papers (2021-10-26T18:44:37Z) - Learning to maximize global influence from local observations [12.611900695498218]
We study a family online influence problems where in a sequence of rounds $t=1,ldots,T$, a decision maker selects one from a large number of agents with the goal of maximizing influence.
The goal of the decision maker is to select the sequence of agents in a way that the total number of influenced nodes in the network.
arXiv Detail & Related papers (2021-09-24T11:59:44Z) - MultiFair: Multi-Group Fairness in Machine Learning [52.24956510371455]
We study multi-group fairness in machine learning (MultiFair)
We propose a generic end-to-end algorithmic framework to solve it.
Our proposed framework is generalizable to many different settings.
arXiv Detail & Related papers (2021-05-24T02:30:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.