DropMix：通过更难的负样本实现更好的图对比学习
DropMix: Better Graph Contrastive Learning with Harder Negative Samples
AI总结：
针对图对比学习中的硬负样本合成，提出DropMix方法，通过局部与全局难度评估选择硬负样本，并在部分维度混合以减少信息丢失，在六个基准数据集上验证了有效性。
摘要：
虽然为对比学习生成更好的负样本已在CV和NLP领域得到广泛研究，但针对图结构数据的工作却很少。最近，Mixup被引入到图对比学习（GCL）中，用于合成硬负样本。然而，由于GCL的无监督学习特性，在没有软标签帮助的情况下，直接混合样本表示可能会无意中导致原始硬负样本的信息丢失，并进一步对新生成的更难负样本的质量产生不利影响。为了解决这个问题，本文提出了一种新方法DropMix来合成更难的负样本，该方法包括两个主要步骤。具体来说，我们首先通过同时从图的局部和全局视角衡量其难度来选择一些硬负样本。之后，我们仅在部分表示维度上混合硬负样本，以生成更难的样本，并减少由Mixup引起的信息丢失。我们进行了大量实验，在六个基准数据集上验证了DropMix的有效性。我们的结果表明，我们的方法可以带来更好的GCL性能。我们的数据和代码可在https://github.com/Mayueq/DropMix-Code公开获取。
英文摘要：
While generating better negative samples for contrastive learning has been widely studied in the areas of CV and NLP, very few work has focused on graph-structured data. Recently, Mixup has been introduced to synthesize hard negative samples in graph contrastive learning (GCL). However, due to the unsupervised learning nature of GCL, without the help of soft labels, directly mixing representations of samples could inadvertently lead to the information loss of the original hard negative and further adversely affect the quality of the newly generated harder negative. To address the problem, in this paper, we propose a novel method DropMix to synthesize harder negative samples, which consists of two main steps. Specifically, we first select some hard negative samples by measuring their hardness from both local and global views in the graph simultaneously. After that, we mix hard negatives only on partial representation dimensions to generate harder ones and decrease the information loss caused by Mixup. We conduct extensive experiments to verify the effectiveness of DropMix on six benchmark datasets. Our results show that our method can lead to better GCL performance. Our data and codes are publicly available at https://github.com/Mayueq/DropMix-Code.
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。
