Sailing in the location-based fairness-bias sphere
Sailing in the location-based fairness-bias sphere
复制标题
在基于位置的公平偏见领域航行
DOI：
10.1145/3557915.3560976
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Ravirathinam, Praveen
中科院分区：
文献类型：
--
作者：
He, Erhu;Xie, Yiqun;Jia, Xiaowei;Chen, Weiye;Bao, Han;Zhou, Xun;Jiang, Zhe;Ghosh, Rahul;Ravirathinam, Praveen
随着机器学习的不断普及，算法的公平性已成为决定其长期成功和可持续性的关键因素。其中，基于位置的公平性-或空间公平性-对于通常依赖于空间数据的各种基本社会应用至关重要，包括农业，灾害响应，城市规划等。如果不加以关注，学习引起的空间偏差可能会导致或加剧资源分配不公平，空间差距，社会分化等。对机器学习中基于位置的公平性和偏见的理解非常有限。与传统的公平性保持技术相比，空间考虑引入了两个主要的复杂层：（1）空间是连续的，没有明确定义的类别（例如，按种族或性别分类）;以及（2）已知通过空间划分给出的分类具有高统计敏感性（例如，gerrymandering）。在这些挑战下，我们正式探索和展示的脆弱性的学习方法在空间公平性偏见领域。具体来说，我们提出了一组技术，可以操纵训练过程朝向各种目标公平偏差结果，同时保持相同水平的整体预测性能（即，“免费”）。广泛的实验进行了两个现实世界的问题：作物监测在美国和棕榈油种植园映射在印度尼西亚。结果表明，操纵算法的有效性和显式调节基于位置的公平性，使用不同的标准集的重要性。
As the adoption of machine learning continues to thrive, fairness of the algorithms has become a key factor determining their long-term success and sustainability. Among them, location-based fairness - or spatial fairness - is critical for a variety of essential societal applications that commonly rely on spatial data, including agriculture, disaster response, urban planning, etc. Spatial biases incurred by learning, if left unattended, may cause or exacerbate unfair distribution of resources, spatial disparity, social division, etc. However, very limited understanding has been developed on location-based fairness and bias in machine learning. Compared to traditional fairness-preserving techniques, the spatial consideration introduces two major layers of complication: (1) Space is continuous with no well-defined categories (e.g., categories by race or gender); and (2) Categorizations given by space-partitionings are known to be subject to high statistical sensitivity (e.g., gerrymandering). Under these challenges, we formally explore and demonstrate the fragility of learning methods in the spatial fairness-bias sphere. Specifically, we present a set of techniques that can maneuver the training process towards various targeted fairness-bias outcomes, while maintaining the same level of overall prediction performance (i.e., for "free"). Extensive experiments are carried out on two real-world problems: crop monitoring in the US and palm oil plantation mapping in Indonesia. The results demonstrate the effectiveness of the manipulation algorithms and the importance of explicitly regulating location-based fairness using a diverse set of criteria.
登录
查看更多内容
通过整合多个数据源改进作物估算
DOI：
--
发表时间：
2017
期刊：
影响因子：
--
作者：
M. Bock;N. Kirkendall
通讯作者：
N. Kirkendall
Spatial-Net：用于空间异构数据集的自适应且与模型无关的深度学习框架
DOI：
10.1145/3474717.3483970
发表时间：
2021
期刊：
Proceedings of the 29th International Conference on Advances in Geographic Information Systems (SIGSPATIAL'21
影响因子：
--
作者：
Xie, Yiqun;Jia, Xiaowei;Bao, Han;Zhou, Xun;Yu, Jia;Ghosh, Rahul;Ravirathinam, Praveen
通讯作者：
Ravirathinam, Praveen
通过无监督预训练学习的图像表示包含类人偏差
DOI：
10.1145/3442188.3445932
发表时间：
2020
期刊：
Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
影响因子：
--
作者：
Ryan Steed;Aylin Caliskan
通讯作者：
Aylin Caliskan
针对空间异质性数据的统计引导深度网络转换和审核框架
DOI：
10.1109/icdm51629.2021.00088
发表时间：
2022
期刊：
2021 IEEE International Conference on Data Mining (ICDM
影响因子：
--
作者：
Xie, Yiqun;He, Erhu;Jia, Xiaowei;Bao, Han;Zhou, Xun;Ghosh, Rahul;Ravirathinam, Praveen
通讯作者：
Ravirathinam, Praveen