FAI: Advancing Deep Learning Towards Spatial Fairness

FAI：推进深度学习迈向空间公平

• 批准号: 2147195
• 负责人: Xiaowei Jia
• 金额: $ 75.51万
• 依托单位: University of Pittsburgh
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2147195&HistoricalAwards=false
• 关键词: FAI; Advancing; Deep; Learning; Towards

The goal of spatial fairness is to reduce biases that have significant linkage to the locations or geographical areas of data samples. Such biases, if left unattended, can cause or exacerbate unfair distribution of resources, social division, spatial disparity, and weaknesses in resilience or sustainability. Spatial fairness is urgently needed for the use of artificial intelligence in a large variety of real-world problems such as agricultural monitoring and disaster management. Agricultural products, including crop maps and acreage estimates, are used to inform important decisions such as the distribution of subsidies and providing farm insurance. Inaccuracies and inequities produced by spatial biases adversely affect these decisions. Similarly, effective and fair mapping of natural disasters such as floods or fires is critical to inform live-saving actions and quantify damages and risks to public infrastructures, which is related to insurance estimation. Machine learning, in particular deep learning, has been widely adopted for spatial datasets with promising results. However, straightforward applications of machine learning have found limited success in preserving spatial fairness due to the variation of data distribution, data quantity, and data quality. The goal of this project is to develop a new generation of learning frameworks to explicitly preserve spatial fairness. The results and code will be made freely available and integrated into existing geospatial software. The methods will also be tested for incorporation in existing real systems (crop and water monitoring). This project aims to advance deep learning methods toward spatial fairness via four innovations. First, new statistical formulations of spatial fairness will be investigated to address unique challenges brought by the continuous spatial domain, particularly due to a variety of ways to partition the space and create location-groups for fairness evaluation, and the fact that statistical conclusions are sensitive to changes in space-partitionings. Second, new network architectures will be developed to improve the spatial fairness by mitigating the conflicts amongst different locations due to the shift of data distribution over space. Third, new fairness-driven adversarial learning strategies will be used to guide the training to converge to parameters that can maintain a high overall solution quality while maximizing spatial fairness across locations. Finally, a knowledge-enhanced approach will be proposed, which integrates general physical relationships to mitigate data-inequality incurred spatial biases, and simulates relevant variables and parameters in underlying physical processes to enhance knowledge-based interpretability of spatial fairness.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

空间公平的目标是减少与数据样本的位置或地理区域有显著联系的偏差。这种偏见如果置之不理，可能导致或加剧资源的不公平分配、社会分裂、空间差距以及复原力或可持续性的弱点。人工智能在农业监测和灾害管理等现实问题中的应用迫切需要空间公平性。农业产品，包括作物分布图和种植面积估计，被用来为诸如补贴分配和提供农业保险等重要决策提供信息。空间偏差造成的不准确和不公平对这些决策产生不利影响。同样，有效和公平地绘制洪水或火灾等自然灾害的地图，对于为拯救生命的行动提供信息和量化公共基础设施的损害和风险至关重要，这与保险估计有关。机器学习，特别是深度学习，已被广泛应用于空间数据集，并取得了可喜的成果。然而，由于数据分布、数据数量和数据质量的变化，机器学习的直接应用在保持空间公平性方面取得了有限的成功。该项目的目标是开发新一代的学习框架，以明确地保持空间公平性。结果和代码将免费提供，并集成到现有的地理空间软件中。还将对这些方法进行测试，以便将其纳入现有的实际系统（作物和水监测）。该项目旨在通过四项创新推动深度学习方法实现空间公平。首先，将研究新的空间公平性统计公式，以解决连续空间域带来的独特挑战，特别是由于空间划分和创建公平评估的位置群的方式多种多样，以及统计结论对空间划分变化的敏感性。其次，将开发新的网络架构，通过减轻由于数据分布在空间上的转移而导致的不同位置之间的冲突来提高空间公平性。第三，将使用新的公平驱动的对抗学习策略来指导训练收敛到能够保持高整体解决方案质量的参数，同时最大限度地提高各个位置的空间公平性。最后，提出了一种知识增强方法，该方法整合了一般物理关系以减轻数据不平等引起的空间偏差，并模拟了潜在物理过程中的相关变量和参数，以增强基于知识的空间公平可解释性。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Sailing in the location-based fairness-bias sphere

在基于位置的公平偏见领域航行

• DOI: 10.1145/3557915.3560976
• 发表时间: 2022
• 期刊: SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information Systems
• 作者: He, Erhu;Xie, Yiqun;Jia, Xiaowei;Chen, Weiye;Bao, Han;Zhou, Xun;Jiang, Zhe;Ghosh, Rahul;Ravirathinam, Praveen
• 通讯作者: Ravirathinam, Praveen

Meta-Transfer Learning: An application to Streamflow modeling in River-streams

• DOI: 10.1109/icdm54844.2022.00026
• 发表时间: 2022-11
• 期刊: 2022 IEEE International Conference on Data Mining (ICDM)
• 作者: Rahul Ghosh;Bangyan Li;Kshitij Tayal;Vipin Kumar;X. Jia

Physics-guided machine learning from simulated data with different physical parameters

• DOI: 10.1007/s10115-023-01864-z
• 发表时间: 2023-03-31
• 期刊: KNOWLEDGE AND INFORMATION SYSTEMS
• 影响因子: 2.7
• 作者: Chen, Shengyu;Kalanat, Nasrin;Jia, Xiaowei
• 通讯作者: Jia, Xiaowei

Statistically-Guided Deep Network Transformation to Harness Heterogeneity in Space (Extended Abstract)

• DOI: 10.24963/ijcai.2022/752
• 发表时间: 2022-07
• 作者: Yiqun Xie;Erhu He;X. Jia;Han Bao;Xun Zhou;Rahul Ghosh;Praveen Ravirathinam

Fairness by “Where”: A Statistically-Robust and Model-Agnostic Bi-level Learning Framework

“Where”的公平性：统计稳健且与模型无关的双层学习框架

• DOI: 10.1609/aaai.v36i11.21481
• 发表时间: 2022
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Xie, Yiqun;He, Erhu;Jia, Xiaowei;Chen, Weiye;Skakun, Sergii;Bao, Han;Jiang, Zhe;Ghosh, Rahul;Ravirathinam, Praveen
• 通讯作者: Ravirathinam, Praveen