用图神经网络捕捉样本间关系，提升自监督学习效果
Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning
- 构建师生双流KNN图，用边表示样本相似性
- 通过多跳消息传递，实现更广域上下文融合
- 在多个数据集上显著超越现有方法
本文提出一种将图论引入自监督表征学习的新方法。传统方法仅关注数据增强带来的样本内部变化，忽视了样本间的相互关系。本方法在预训练阶段为教师和学生流分别构建k近邻（KNN）图，节点为样本及其隐含表征，边表示实例间的相似性。预训练后引入表征精炼阶段，利用图神经网络（GNN）在多跳范围内传播信息，实现更广泛的上下文整合。在CIFAR-10、ImageNet-100和ImageNet-1K上的实验表明，该方法分别较当前最优方法提升7.3%、3.2%和1.0%的准确率，验证了基于图机制的有效性。代码已公开于https://github.com/alijavidani/SSL-GraphNNCLR。
原文摘要 · Abstract (English)
This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing k-nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph based mechanism. The code is publicly available at https://github.com/alijavidani/SSL-GraphNNCLR.
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。