Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (17): 328-333.DOI: 10.3778/j.issn.1002-8331.2207-0441

• Engineering and Applications • Previous Articles     Next Articles

Novel Graph Semi-Supervised Transduction Approach with Improved Gauss Kernel for Few-Shot Learning

PAN Xueling, LI Guohe, YU Qiuyue, GUO Kai, LI Zheng   

  1. 1.Beijing Key Lab of Petroleum Data Mining, China University of Petroleum, Beijing 102249, China
    2.College of Information Science and Engineering, China University of Petroleum, Beijing 102249, China
  • Online:2023-09-01 Published:2023-09-01

结合改进高斯核的图半监督转导小样本学习

潘雪玲,李国和,于秋月,郭凯,李铮   

  1. 1.中国石油大学(北京) 石油数据挖掘北京市重点实验室,北京 102249
    2.中国石油大学(北京) 信息科学与工程学院,北京 102249

Abstract: Few-shot learning is one of the most significant research in machine learning. In recent years, deep learning has made great progress in machine learning and is widely used in various industries. However, it requires a large amount of annotated data to train the model, which costs a lot of resources. Therefore, few-shot learning has gradually become one of the research hotspots of machine learning. To improve the accuracy of the few-shot learning model, in this paper, a novel graph semi-supervised transduction propagation network model with an improved Gaussian kernel function(IG-semiTPN) is presented to solve the problem that the attenuation rate of the Gaussian kernel is almost zero in infinite. The parameters of displacement and correction are introduced to the model to make it have a fast attenuation rate near the test point and maintain a moderate attenuation in the infinite in the high-dimensional feature space, to improve the effectiveness of the few-shot learning model. Experimental results show that the proposed approach can improve the accuracy to a certain extent and has practical value.

Key words: few-shot learning, meta learning, improved Gauss kernel, graph semi-supervision learning, label propagation

摘要: 近年来,深度学习在机器学习领域取得巨大的研究进展,广泛应用于各个行业。但其需要大量地标注数据训练模型,资源成本耗费较大。因此,小样本学习逐渐成为机器学习的研究热点之一,并可结合半监督学习解决小样本学习标注数据少的问题。为了提高小样本学习模型准确率,针对半监督转导传播网络模型中高斯核在无限远处的衰减几乎为零的问题,提出适用于半监督转导网络模型的改进高斯核函数。通过加入位移参数和修正参数,使其在高维特征空间中能在测试点附近具有较快的衰减速度且在无限远处仍能保持适度的衰减,提高了小样本学习模型效果。在监督和半监督环境下进行实验对比,实验结果表明该算法在一定程度上提高模型精度,且具有实用价值。

关键词: 小样本学习, 元学习, 改进高斯核, 图半监督学习, 标签传播