Heterogeneous fairness algorithm based on federated learning in intelligent transportation system

With the development of the Intelligent Transportation System, various distributed sensors (including GPS, radar, infrared sensors) process massive data and make decisions for emergencies. Federated learning is a new distributed machine learning paradigm, in which system heterogeneity is the difficulty of fairness design. This paper designs a system heterogeneous fair federated learning algorithm (SHFF). SHFF introduces the equipment influence factor I into the optimization target and dynamically adjusts the equipment proportion with other performance. By changing the global fairness parameter θ, the algorithm can control fairness according to the actual needs. Experimental results show that, compared with the popular q-FedAvg algorithm, the SHFF algorithm proposed in this paper improves the average accuracy of the Worst 10% by 26% and reduces the variance by 61%.

Connective Action for Global Fairness: Building Social Imaginaries

Social imaginaries are frameworks within which people organise their collective world; where imagination, not simply reason, plays a part in the construction of social practices. Through a grounded theory approach, this article asks whether and how social imaginaries of global fairness are present in connective action, a type of digital interaction for advocacy. From January 2014 to June 2015, the study followed the Facebook accounts of five advocacy organisations: Hivos, Oxfam IBIS, Intermon-Oxfam, SSNC and Vredeseilanden. Connective action, more than just accomplishing an expressing function of posting and sharing – which could be considered as ‘slacktivism’– denotes cooperating and acting by means of dialogic learning involving reflection and action. The research suggests that current social imaginaries may be built in connective action involving topics of nature conservation, equality, eco-farming, among others. Thus, the field of connective action remains open to theorizing how these imaginaries could constitute a strong foundation upon which communication for social change (CFSC) strategies may be grounded.