We study one of the most popular problems in **neurosymbolic learning** (NSL), that of learning neural classifiers given only the result of applying a symbolic component $σ$ to the gold labels of the elements of a vector $\mathbf x$. The gold labels of the elements in $\mathbf x$ are unknown to the learner. We make multiple contributions, theoretical and practical, to address a problem that has not been studied so far in this context, that of characterizing and mitigating *learning imbalances*, i.e., major differences in the errors that occur when classifying instances of different classes (aka **class-specific risks**). Our theoretical analysis reveals a unique phenomenon: that $σ$ can greatly impact learning imbalances. This result sharply contrasts with previous research on supervised and weakly supervised learning, which only studies learning imbalances under data imbalances. On the practical side, we introduce a technique for estimating the marginal of the hidden gold labels using weakly supervised data. Then, we introduce algorithms that mitigate imbalances at training and testing time by treating the marginal of the hidden labels as a constraint. We demonstrate the effectiveness of our techniques using strong baselines from NSL and long-tailed learning, suggesting performance improvements of up to 14%.
Neurosymbolic Learning for Advanced Persistent Threat Detection under Extreme Class Imbalance
1 Center for Secure \& Intelligent Critical Systems；School of Cybersecurity, Old Dominion University, VA, USA；2 Department of Computer Engineering, University of Isfahan, Iran；3 Faculty of Engineering Modern Technologies, Amol University of Special Modern Technologies, Iran；4 Department of Electrical；Computer Engineering, Worcester Polytechnic Institute, MA, USA；5 Department of Electrical；Department of Computer Science Old Dominion University VA, USA；Department of Computer Engineering, University of Isfahan, Isfahan, Iran \& Center for Secure \& Intelligent Critical Systems, Old Dominion University, VA, USA；Faculty of Engineering Modern Technologies Amol University of Special Modern Technologies Amol, Iran；Department of Electrical；Computer Engineering Worcester Polytechnic Institute MA, USA；Center for Secure \& Intelligent Critical Systems Old Dominion University VA, USA；Bradley Department of Electrical \& Computer Engineering Virginia Tech, Arlington VA, USA
Improving Group Fairness in Tensor Completion via Imbalance Mitigating Entity Augmentation
Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA（计算机科学与工程系，加州大学河滨分校）；Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL, USA（计算与数据科学学院，伊利诺伊大学厄巴纳-香槟分校）
PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University（教育区块链与智能技术重点实验室，教育部，广西师范大学）；Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University（广西多源信息挖掘与安全重点实验室，广西师范大学）；School of Software, Beihang University（北京航空航天大学软件学院）；SKLCCSE, School of Computer Science and Engineering, Beihang University（SKLCCSE，北京航空航天大学计算机科学与工程学院）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）
Mitigating Participation Imbalance Bias in Asynchronous Federated Learning
University of California, Riverside（加州大学河滨分校）；Indian Institute of Science（印度科学研究院）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；DEVCOM Army Research Laboratory（陆军研究实验室）
A Machine Learning Framework for Handling Unreliable Absence Label and Class Imbalance for Marine Stinger Beaching Prediction
Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics（过渡人工智能研究组与数学与统计学院）；School of Mathematics and Statistics（数学与统计学院）；Center for Marine Science and Innovation（海洋科学与创新中心）
Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Singapore University of Technology and Design（新加坡科技设计大学）；School of Software, Zhejiang University（浙江大学软件学院）
