arXiv subjects

Amirarsalan Rajabi

Publications and source records attributed to Amirarsalan Rajabi.

6 recordsLinked to original sources

arXiv2022

Through a fair looking-glass: mitigating bias in image datasets

With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified. Many previous methods for image dataset de-biasing, including models based on augmenting datasets, are computationally expensive to implement. In this study, we present a fast and effective model to de-bias an image dataset through reconstruction and minimizing the statistical dependence between intended variables. Our architecture includes a U-net to reconstruct images, combined with a pre-trained classifier which penalizes the statistical dependence between target attribute and the protected attribute. We evaluate our proposed model on CelebA dataset, compare the results with a state-of-the-art de-biasing method, and show that the model achieves a promising fairness-accuracy combination.

cs.CV↗

arXiv2021

TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks

With the increasing reliance on automated decision making, the issue of algorithmic fairness has gained increasing importance. In this paper, we propose a Generative Adversarial Network for tabular data generation. The model includes two phases of training. In the first phase, the model is trained to accurately generate synthetic data similar to the reference dataset. In the second phase we modify the value function to add fairness constraint, and continue training the network to generate data that is both accurate and fair. We test our results in both cases of unconstrained, and constrained fair data generation. In the unconstrained case, i.e. when the model is only trained in the first phase and is only meant to generate accurate data following the same joint probability distribution of the real data, the results show that the model beats state-of-the-art GANs proposed in the literature to produce synthetic tabular data. Also, in the constrained case in which the first phase of training is followed by the second phase, we train the network and test it on four datasets studied in the fairness literature and compare our results with another state-of-the-art pre-processing method, and present the promising results that it achieves. Comparing to other studies utilizing GANs for fair data generation, our model is comparably more stable by using only one critic, and also by avoiding major problems of original GAN model, such as mode-dropping and non-convergence, by implementing a Wasserstein GAN.

cs.LG↗

arXiv2020

Review on Learning and Extracting Graph Features for Link Prediction

Link prediction in complex networks has attracted considerable attention from interdisciplinary research communities, due to its ubiquitous applications in biological networks, social networks, transportation networks, telecommunication networks, and, recently, knowledge graphs. Numerous studies utilized link prediction approaches in order sto find missing links or predict the likelihood of future links as well as employed for reconstruction networks, recommender systems, privacy control, etc. This work presents an extensive review of state-of-art methods and algorithms proposed on this subject and categorizes them into four main categories: similarity-based methods, probabilistic methods, relational models, and learning-based methods. Additionally, a collection of network data sets has been presented in this paper, which can be used in order to study link prediction. We conclude this study with a discussion of recent developments and future research directions.

cs.SI↗

arXiv2020

A Stance Data Set on Polarized Conversations on Twitter about the Efficacy of Hydroxychloroquine as a Treatment for COVID-19

At the time of this study, the SARS-CoV-2 virus that caused the COVID-19 pandemic has spread significantly across the world. Considering the uncertainty about policies, health risks, financial difficulties, etc. the online media, specially the Twitter platform, is experiencing a high volume of activity related to this pandemic. Among the hot topics, the polarized debates about unconfirmed medicines for the treatment and prevention of the disease have attracted significant attention from online media users. In this work, we present a stance data set, COVID-CQ, of user-generated content on Twitter in the context of COVID-19. We investigated more than 14 thousand tweets and manually annotated the opinions of the tweet initiators regarding the use of "chloroquine" and "hydroxychloroquine" for the treatment or prevention of COVID-19. To the best of our knowledge, COVID-CQ is the first data set of Twitter users' stances in the context of the COVID-19 pandemic, and the largest Twitter data set on users' stances towards a claim, in any domain. We have made this data set available to the research community via GitHub. We expect this data set to be useful for many research purposes, including stance detection, evolution and dynamics of opinions regarding this outbreak, and changes in opinions in response to the exogenous shocks such as policy decisions and events.

cs.SI↗

arXiv2020

CD-SEIZ: Cognition-Driven SEIZ Compartmental Model for the Prediction of Information Cascades on Twitter

Information spreading social media platforms has become ubiquitous in our lives due to viral information propagation regardless of its veracity. Some information cascades turn out to be viral since they circulated rapidly on the Internet. The uncontrollable virality of manipulated or disorientated true information (fake news) might be quite harmful, while the spread of the true news is advantageous, especially in emergencies. We tackle the problem of predicting information cascades by presenting a novel variant of SEIZ (Susceptible/ Exposed/ Infected/ Skeptics) model that outperforms the original version by taking into account the cognitive processing depth of users. We define an information cascade as the set of social media users' reactions to the original content which requires at least minimal physical and cognitive effort; therefore, we considered retweet/ reply/ quote (mention) activities and tested our framework on the Syrian White Helmets Twitter data set from April 1st, 2018 to April 30th, 2019. In the prediction of cascade pattern via traditional compartmental models, all the activities are grouped, and their summation is taken into account; however, transition rates between compartments should vary according to the activity type since their requirements of physical and cognitive efforts are not same. Based on this assumption, we design a cognition-driven SEIZ (CD-SEIZ) model in the prediction of information cascades on Twitter. We tested SIS, SEIZ, and CD-SEIZ models on 1000 Twitter cascades and found that CD-SEIZ has a significantly low fitting error and provides a statistically more accurate estimation.

cs.SI↗

arXiv2020

Resistance of communities against disinformation

The spread of disinformation is considered a big threat to societies and has recently received unprecedented attention. In this paper we propose an agent-based model to simulate dissemination of a conspiracy in a population. The model is able to compare the resistance of different network structures against the activity of conspirators. Results show that connectedness of network structure and centrality of conspirators are of crucial importance in preventing conspiracies from becoming widespread.

cs.SI↗