[论文解读] Proceedings of the IJCAI 2017 Workshop on Learning in the Presence of Class Imbalance and Concept Drift (LPCICD'17)

Shuo Wang, Leandro L. Minku+2 more|arXiv (Cornell University)|Jul 28, 2017

Data Stream Mining Techniques参考文献 15被引用 4

一句话总结

本研讨会论文集探讨了机器学习中类别不平衡与概念漂移的联合挑战，提出整合性方法以提升模型在真实数据流中的鲁棒性。研究强调了不平衡处理与漂移检测之间的相互干扰，主张采用自适应、双重视觉的算法，在动态、偏斜的数据分布下维持预测性能。

ABSTRACT

With the wide application of machine learning algorithms to the real world, class imbalance and concept drift have become crucial learning issues. Class imbalance happens when the data categories are not equally represented, i.e., at least one category is minority compared to other categories. It can cause learning bias towards the majority class and poor generalization. Concept drift is a change in the underlying distribution of the problem, and is a significant issue specially when learning from data streams. It requires learners to be adaptive to dynamic changes. Class imbalance and concept drift can significantly hinder predictive performance, and the problem becomes particularly challenging when they occur simultaneously. This challenge arises from the fact that one problem can affect the treatment of the other. For example, drift detection algorithms based on the traditional classification error may be sensitive to the imbalanced degree and become less effective; and class imbalance techniques need to be adaptive to changing imbalance rates, otherwise the class receiving the preferential treatment may not be the correct minority class at the current moment. Therefore, the mutual effect of class imbalance and concept drift should be considered during algorithm design. The aim of this workshop is to bring together researchers from the areas of class imbalance learning and concept drift in order to encourage discussions and new collaborations on solving the combined issue of class imbalance and concept drift. It provides a forum for international researchers and practitioners to share and discuss their original work on addressing new challenges and research issues in class imbalance learning, concept drift, and the combined issues of class imbalance and concept drift. The proceedings include 8 papers on these topics.

研究动机与目标

• 应对现实机器学习应用中类别不平衡与概念漂移日益严峻的挑战。
• 研究类别不平衡技术与概念漂移检测机制之间的相互干扰。
• 推动协同研究，设计能同时处理两类问题的自适应算法。
• 为研究人员提供一个分享数据流中不平衡与漂移联合问题解决方案的平台。
• 通过整合两个研究领域的洞见，推进从动态、不平衡数据中学习的前沿技术。

提出的方法

• 在 IJCAI 2017 上组织专门研讨会，汇聚类别不平衡学习与概念漂移领域的专家。
• 收集并发表 8篇原创研究论文，探讨类别不平衡、概念漂移及其联合影响。
• 通过推广能够适应变化的类别分布和不平衡率的算法，促进方法论的整合。
• 推动讨论传统基于误差的漂移检测在不平衡环境下的局限性。
• 支持开发能够根据当前数据分布动态调整类别偏好的学习系统。
• 利用协作性、跨学科的论坛，探索在漂移与不平衡条件下保持公平性与准确性的混合解决方案。

实验结果

研究问题

• RQ1 类别不平衡在多大程度上影响传统概念漂移检测算法的性能？
• RQ2 概念漂移在多大程度上使标准类别不平衡缓解技术的应用复杂化？
• RQ3 是否可以设计出能同时适应数据分布变化与类别不平衡率演化的学习算法？
• RQ4 在数据流环境中，当不平衡与漂移同时发生时，其关键故障模式是什么？
• RQ5 现有方法应如何修改，以确保在动态条件下少数类始终是学习的重点？

主要发现

• 类别不平衡会显著降低基于分类误差的传统漂移检测方法的有效性。
• 对误差率敏感的漂移检测算法在数据高度不平衡时可能无法识别概念变化。
• 若未随不平衡率变化而自适应，标准类别不平衡技术可能无意中偏向错误的少数类。
• 类别不平衡与概念漂移的共现造成复杂交互，损害公平性与准确性。
• 迫切需要能够实时联合建模并适应不平衡与漂移的算法。
• 研讨会论文集突出了将不平衡处理与漂移适应整合到统一学习框架中的新兴研究方向。