arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.01916cs.LGcs.AIcs.NE
收藏

面向多领域不平衡数据的领域感知对比知识转移

Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data

UIC(伊利诺伊大学芝加哥分校);Amazon Alexa AI(亚马逊Alexa人工智能部门)

Zixuan Ke, Mohammad Kachuee, Sungjin Lee

摘要:

在许多现实世界的机器学习应用中,样本属于一组域,对于产品评论,每个评论属于一个产品类别。本文研究了多领域不平衡学习问题,即类与领域之间存在不平衡的情况。在MIL环境中,不同的领域表现出不同的模式,并且在领域之间存在不同程度的相似性和差异,这为迁移学习带来了机遇和挑战,特别是当面临有限或不足的训练数据时。提出了一种新的领域感知的对比知识转移方法DCMI(Domain-aware Contrast Knowledge Transfer),该方法(1)识别共享领域知识,以鼓励相似领域之间的正转移(特别是从头域到尾域);(2)隔离特定领域知识,以最小化来自不相似领域的负转移。我们在三个不同的数据集上评估了DCMI的性能,在不同的MIL场景中显示出显着的改进。

英文摘要:

In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study multi-domain imbalanced learning (MIL), the scenario that there is imbalance not only in classes but also in domains. In the MIL setting, different domains exhibit different patterns and there is a varying degree of similarity and divergence among domains posing opportunities and challenges for transfer learning especially when faced with limited or insufficient training data. We propose a novel domain-aware contrastive knowledge transfer method called DCMI to (1) identify the shared domain knowledge to encourage positive transfer among similar domains (in particular from head domains to tail domains); (2) isolate the domain-specific knowledge to minimize the negative transfer from dissimilar domains. We evaluated the performance of DCMI on three different datasets showing significant improvements in different MIL scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑