通过标签分布优化多标签对比学习，提升表示效果。
Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
- 仅凭标签交集选择正负样本，简化流程
- 用RBF和对比损失重构标签分布，捕捉标签关系
- 在9个数据集上6项指标领先现有方法
在多标签学习中，利用对比学习获取更好表征面临的核心挑战是正负样本的选择及标签信息的有效利用。以往方法基于标签重叠选择正负样本，并用于标签级损失平衡，但存在选择过程复杂且未考虑不同标签重要性差异的问题。为此，本文提出一种基于标签分布的新型多标签对比学习方法。在正负样本选择时，仅需判断标签是否存在交集；为建模标签间关系，提出两种从逻辑标签中恢复标签分布的方法，分别基于径向基函数（RBF）和对比损失。在九个常用多标签数据集（涵盖图像与向量数据）上的实验表明，该方法在六项评估指标上优于当前最优方法。
原文摘要 · Abstract (English)
In multi-label learning, leveraging contrastive learning to learn better representations faces a key challenge: selecting positive and negative samples and effectively utilizing label information. Previous studies selected positive and negative samples based on the overlap between labels and used them for label-wise loss balancing. However, these methods suffer from a complex selection process and fail to account for the varying importance of different labels. To address these problems, we propose a novel method that improves multi-label contrastive learning through label distribution. Specifically, when selecting positive and negative samples, we only need to consider whether there is an intersection between labels. To model the relationships between labels, we introduce two methods to recover label distributions from logical labels, based on Radial Basis Function (RBF) and contrastive loss, respectively. We evaluate our method on nine widely used multi-label datasets, including image and vector datasets. The results demonstrate that our method outperforms state-of-the-art methods in six evaluation metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。