Federated Learning (FL) has emerged as a result of data ownership and privacy concerns to prevent data from being shared between multiple parties included in a training procedure. Although issues, such as privacy, have gained significant attention in this domain, not much attention has been given to satisfying statistical fairness measures in the FL setting. With this goal in mind, we conduct studies to show that FL is able to satisfy different fairness metrics under different data regimes consisting of different types of clients. More specifically, uncooperative or adversarial clients might contaminate the global FL model by injecting biased or poisoned models due to existing biases in their training datasets. Those biases might be a result of imbalanced training set (Zhang and Zhou 2019), historical biases (Mehrabi et al. 2021a), or poisoned data-points from data poisoning attacks against fairness (Mehrabi et al. 2021b; Solans, Biggio, and Castillo 2020). Thus, we propose a new FL framework that is able to satisfy multiple objectives including various statistical fairness metrics. Through experimentation, we then show the effectiveness of this method comparing it with various baselines, its ability in satisfying different objectives collectively and individually, and its ability in identifying uncooperative or adversarial clients and down-weighing their effect
翻译:联邦学习(FL)之所以出现,是因为数据所有权和隐私问题,以防止数据在培训程序中包括的多方当事人之间共享数据,因此出现了联邦学习(FL),因为数据所有权和隐私问题,防止数据在培训程序中的多个当事方之间共享,尽管隐私等问题在这一领域引起了极大关注,但在这一领域,虽然隐私等问题已引起重视,但并未十分关注满足FL环境中的统计公平措施,铭记这一目标,我们开展研究表明FL能够在由不同类型客户组成的不同数据制度下满足不同的公平度度;更具体地说,不合作或敌对客户可能因培训数据集中的现有偏偏偏差或有毒模式,通过输入有偏见或有毒的模型,污染全球FL模式,从而污染全球FL模式,这些偏见可能由于培训数据集中存在的偏见或有毒模型,这些偏见可能在这一领域引起极大关注,尽管在这方面的问题,例如隐私问题等,虽然在这一领域已引起极大关注,但这一领域的问题可能由于以下原因,例如隐私问题,例如隐私问题等,而在这一领域已在这一领域内已引起极大关注,而引起极大关注;虽然在这方面的问题,但并未引起重视,但并未充分重视,虽然在这方面的问题,但并未重视,尽管在这方面的问题,尽管在这方面,但并未重视,但并未重视,尽管在这一领域内没有受到重视,但并未在FL(Zhang和Zhhhang和Zhhhhhhow 2019 2019)、历史偏见,或Zhbbbb和Z2021ab),或2019、历史偏见,或2021ab偏见,或2021aaaaaa、历史偏见、历史偏见,或由于历史偏见,或数据偏偏偏偏偏偏偏偏偏偏偏偏偏偏偏偏差,或数据点,或数据中,或数据导致,或数据中的数据点,或数据中的数据点可能使,或2021a,或数据攻击(M(M(Mea),或2021a),或数据攻击(Ma),或2021a),或数据对数据攻击,或数据攻击没有考虑到数据攻击、历史偏见,或数据攻击(Ma),或数据攻击(M),或2021a),或数据对数据对数据攻击,或数据对数据对数据攻击、历史偏见,或数据攻击(M-2021a),或