论文标题
学会在嘈杂的亲和力图上可靠地传播
Learn to Propagate Reliably on Noisy Affinity Graphs
论文作者
论文摘要
最近的工作表明，通过标签传播来利用未标记的数据可以大大降低标签成本，这在开发视觉识别模型中一直是一个关键问题。但是，如何可靠地传播标签，尤其是在具有未知异常值的数据集上，仍然是一个悬而未决的问题。诸如线性扩散之类的常规方法缺乏处理复杂图结构的能力，并且当种子稀疏时性能较差。基于图形神经网络的最新方法将面临性能下降的困难，因为它们扩展到嘈杂的图形。为了克服这些困难，我们提出了一个新框架，该框架允许在大规模的现实世界数据上可靠地传播标签。该框架结合了（1）局部图神经网络，以在维持高可扩展性的同时准确地预测不同的局部结构，以及（2）基于置信的路径调度程序，以谨慎的方式识别异常值并向前移动传播前沿。 ImageNet和MS-Celeb-1m的实验表明，我们的置信度引导框架可以显着提高传播标签的整体精度，尤其是当图非常嘈杂时。
Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models. Yet, how to propagate labels reliably, especially on a dataset with unknown outliers, remains an open question. Conventional methods such as linear diffusion lack the capability of handling complex graph structures and may perform poorly when the seeds are sparse. Latest methods based on graph neural networks would face difficulties on performance drop as they scale out to noisy graphs. To overcome these difficulties, we propose a new framework that allows labels to be propagated reliably on large-scale real-world data. This framework incorporates (1) a local graph neural network to predict accurately on varying local structures while maintaining high scalability, and (2) a confidence-based path scheduler that identifies outliers and moves forward the propagation frontier in a prudent way. Experiments on both ImageNet and Ms-Celeb-1M show that our confidence guided framework can significantly improve the overall accuracies of the propagated labels, especially when the graph is very noisy.
