MMMehdi Mashayekhi

Mehdi Mashayekhi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mehdi Mashayekhi has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning

    by Aditya Srinivas Timmaraju, Mehdi Mashayekhi, Mingliang Chen, Qi Zeng, Quintin Fettes, Wesley Cheung, Yihan Xiao, Manojkumar Rangasamy Kannadasan, Pushkar Tripathi, Sean Gahagan, et al.

    Variances in ad impression outcomes across demographic groups are increasingly considered to be potentially indicative of algorithmic bias in personalized ads systems. While there are many definitions of fairness that could be applicable in the context of personalized systems, we present a framework which we call the Variance Reduction System (VRS) for achieving more equitable outcomes in Meta's ads systems. VRS seeks to achieve a distribution of impressions with respect to selected protected class (PC) attributes that more closely aligns the demographics of an ad's eligible audience (a function of advertiser targeting criteria) with the audience who sees that ad, in a privacy-preserving manner. We first define metrics to quantify fairness gaps in terms of ad impression variances with respect to PC attributes including gender and estimated race. We then present the VRS for re-ranking ads in an impression variance-aware manner. We evaluate VRS via extensive simulations over different parameter choices and study the effect of the VRS on the chosen fairness metric. We finally present online A/B testing results from applying VRS to Meta's ads systems, concluding with a discussion of future work. We have deployed the VRS to all users in the US for housing ads, resulting in significant improvement in our fairness metric. VRS is the first large-scale deployed framework for pursuing fairness for multiple PC attributes in online advertising.


  • Open Access

    Prosocial Norm Emergence in Multi-agent Systems

    by Mehdi Mashayekhi, Nirav Ajmeri, George F. List, Munindar P. Singh

    Multi-agent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains. We consider a setting where not only the member agents are adaptive but also the multi-agent system viewed as an entity in its own right is adaptive. Specifically, the social structure of a multi-agent system can be reflected in the social norms among its members. It is well recognized that the norms that arise in society are not always beneficial to its members. We focus on prosocial norms, which help achieve positive outcomes for society and often provide guidance to agents to act in a manner that takes into account the welfare of others. Specifically, we propose Cha, a framework for the emergence of prosocial norms. Unlike previous norm emergence approaches, Cha supports continual change to a system (agents may enter and leave) and dynamism (norms may change when the environment changes). Importantly, Cha agents incorporate prosocial decision-making based on inequity aversion theory, reflecting an intuition of guilt arising from being antisocial. In this manner, Cha brings together two important themes in prosociality: decision-making by individuals and fairness of system-level outcomes. We demonstrate via simulation that Cha can improve aggregate societal gains and fairness of outcomes.


  • Open Access

    Prosocial Norm Emergence in Multiagent Systems

    by Mehdi Mashayekhi, Nirav Ajmeri, George F. List, Munindar P. Singh

    Multiagent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains. We consider a setting where not only the member agents are adaptive but also the multiagent system viewed as an entity in its own right is adaptive. Specifically, the social structure of a multiagent system can be reflected in the social norms among its members. It is well recognized that the norms that arise in society are not always beneficial to its members. We focus on prosocial norms, which help achieve positive outcomes for society and often provide guidance to agents to act in a manner that takes into account the welfare of others. Specifically, we propose Cha, a framework for the emergence of prosocial norms. Unlike previous norm emergence approaches, Cha supports continual change to a system (agents may enter and leave) and dynamism (norms may change when the environment changes). Importantly, Cha agents incorporate prosocial decision making based on inequity aversion theory, reflecting an intuition of guilt arising from being antisocial. In this manner, Cha brings together two important themes in prosociality: decision making by individuals and fairness of system-level outcomes. We demonstrate via simulation that Cha can improve aggregate societal gains and fairness of outcomes.

  • Open Access

    Development of a Transportation System Simulation Manual Framework: From Theory to Practice

    by George List, Mehdi Mashayekhi, Robert L. Bertini, Brandon Nevers

    After several decades of advances, simulation has become an important tool in the modeling of transportation systems and is widely applied in practice. Guides have been created by organizations in several countries, and dozens of papers have been published in scientific journals on the theory and application of transport simulation; these works are aimed at guiding practitioners in the use of simulation tools. However, transport simulation still lacks a unified and comprehensive guide for use in practice. The lack of such a document leads to conflicts between modelers, agencies, and decision makers and allows inappropriate use of the models. The outcome is often inaccurate results, inefficient use of resources, and conflict. This paper reviews and analyzes the existing transportation simulation guides. It identifies gaps and limitations and proposes an outline for a comprehensive simulation manual that is based on stakeholder input. Review of the existing guidance documents reveals that almost all these documents focus on traffic operations, and they provide either broad guidelines for building simulation models or advice on using a specific software product. Other issues, particularly those related to topics such as safety assessments, environmental impacts, public transportation, pedestrians, bicycles, simulation algorithms, agent-based simulation, and multimodal simulation, are addressed in only a cursory fashion. This paper proposes a possible structure for a transportation system simulation manual that would cover the limitations and gaps in the existing literature. The proposed document would consist of five volumes: concepts, model building, verification and validation, results analysis, and case studies and supplementary materials.


  • Application of Soft Computing for Prediction of Pavement Condition Index

    by Habib Shahnazari, Mohammad A. Tutunchian, Mehdi Mashayekhi, Amir A. Amini

    The pavement condition index (PCI) is a widely used numerical index for the evaluation of the structural integrity and operational condition of pavements. Estimation of the PCI is based on the results of a visual inspection in which the type, severity, and quantity of distresses are identified. The purpose of this study is to develop an alternative approach for forecasting the PCI using optimization techniques, including artificial neural networks (ANN) and genetic programming (GP). The proposed soft computing method can reliably estimate the PCI and can be used in a pavement management system (PMS) using simple and accessible spreadsheet softwares. A database composed of the PCI results of more than 1,250 km of highways in Iran was used to develop the models. The results showed that the ANN- and GP-based projected values are in good agreement with the field-measured data. In addition, the ANN-based model was more precise than the GP-based model. For more straightforward applications, a computer p...