Advanced Seminar

Spatial Fairness in Algorithmic Decision Making: Concepts, Detection, and Mitigation

Organizers:
Dimitris Kyriakopoulos (Athena Research Center, Greece)
Dimitris Sacharidis (Université Libre de Bruxelles, Belgium)
Giorgos Giannopoulos (National Observatory of Athens and Athena Research Center, Greece)

Abstract: AI tools and applications are increasingly becoming part of many aspects of our lives, including social, economic, and professional domains. Going beyond functionalities such as simple recommendations, AI applications are also widely being used for decision assistance/support and decision-making. Combined with the largely black-box nature of current state-of-the-art algorithms, this has raised substantial concerns regarding the fairness of such algorithmic decision-making/support systems. To this end, a plethora of fairness and bias definitions have been proposed in the literature, along with methods for auditing, detecting, and mitigating bias. These methods operate either at the pre-processing stage (repairing the training data), the in-processing stage (intervening during the training of the AI model), or the post-processing stage (correcting the model’s decisions). In this seminar, we focus on spatial fairness, i.e., the notion that the distribution of a model’s decisions should not be affected (positively or negatively) by the location of the instances on which the decisions are made. We first provide a brief introduction to general-purpose AI fairness, including prominent fairness notions, definitions, and detection and mitigation techniques. We then proceed to discuss spatial fairness, presenting a categorization of its different interpretations and the types of techniques applied. We subsequently focus on the most prominent state-of-the-art methods for spatial bias detection and mitigation. The seminar concludes with a discussion of open challenges and future directions for research in this area.

Human-enabled Edge Computing: Convergence of Mobile CrowdSensing and Multi-access Edge Computing for Next-Generation Smart Systems

Organizers:
Luca Foschini (University of Bologna)
Michele Girolami (ISTI-CNR)

Abstract: Mobile CrowdSensing (MCS) enables collective data harvesting actions by coordinating citizens willing to contribute data collected via their wearable devices. Meaningful examples include smartphone, wristband and smart watches all equipped with sensing units as well as WiFi network interfaces. Such devices can potentially provide an incredible source of information in urban environments, useful to collect dataset with an unseen granularity and accuracy. One of the biggest challenges in a real-world MCS system lies in the capacity to increase the amount of data collected from volunteers, but also to efficiently exploit the communication network in order to retrieve data by reducing latency and preserve battery consumption volunteer’s devices. To this end, the MCS and Multi- access Edge Computing (MEC) paradigms can be considered as complementary approaches opening to new sensing scenarios. The goal of this advanced seminar is to introduce the audience to MCS techniques with a holistic approach. The advanced seminar is organized in two sections. The first part of the seminar will cover some key-concepts of MCS, while the second part will focus on the convergence of MCS and MEC by describing some architecture designs toward the realization of the novel Human-enabled Edge Computing (HEC) model. The advanced seminar will also offer examples to guide the audience through a step-by-step process in an exploratory data analysis with a real-world MCS dataset, namely the ParticipAct living lab. The advanced seminar will finally conclude with some of the most challenging barriers to realize real into-the-wild MCS campaigns as well as some research challenges.