arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.07383cs.LGcs.CV
收藏

基于自动编码器的在线深度学习

Online Deep Learning based on Auto-Encoder

China University of Petroleum(中国石油大学);College of Information Science and Engineering(信息科学与工程学院)

Si-si Zhang, Jian-wei Liu, Xin Zuo, Run-kun Lu, Si-ming Lian

摘要:

在线学习是素描海量实时高速数据的重要技术手段。虽然这一方向已经引起了广泛的关注,但这方面的文献大多忽略了以下三个问题:(1)它们很少考虑存在于实例中的潜在的抽象层次信息,即使提取这些抽象层次潜在表示有助于更好地预测实例的类标签;(2)在未知数据点上预分配模型的思想不适用于具有演化概率分布的流数据建模。这种挑战被称为模型灵活性。因此,考虑到这一点,我们需要设计的在线深度学习模型应该具有可变的底层结构;(3)此外,融合这些抽象层次潜在表示以实现更好的分类性能至关重要,并且在处理数据分布变化的数据流时,我们应该对不同层次的隐式表示信息赋予不同的权重。为了解决这些问题,我们提出了一种基于自动编码器的两阶段在线深度学习(ODLAE)。基于自动编码器,考虑重构损失,提取实例的抽象层次潜在表示;基于预测损失,设计了两种融合策略:输出级融合策略,将编码器的分类结果融合到各隐层;特征级融合策略,利用自注意机制融合各隐层输出。最后,为了提高算法的鲁棒性,我们还尝试利用去噪自动编码器来产生层次潜在表示。在不同数据集上的实验结果验证了我们提出的算法(ODLAE)的有效性,优于几个基线。

英文摘要:

Online learning is an important technical means for sketching massive real-time and high-speed data. Although this direction has attracted intensive attention, most of the literature in this area ignore the following three issues: (1) they think little of the underlying abstract hierarchical latent information existing in examples, even if extracting these abstract hierarchical latent representations is useful to better predict the class labels of examples; (2) the idea of preassigned model on unseen datapoints is not suitable for modeling streaming data with evolving probability distribution. This challenge is referred as model flexibility. And so, with this in minds, the online deep learning model we need to design should have a variable underlying structure; (3) moreover, it is of utmost importance to fusion these abstract hierarchical latent representations to achieve better classification performance, and we should give different weights to different levels of implicit representation information when dealing with the data streaming where the data distribution changes. To address these issues, we propose a two-phase Online Deep Learning based on Auto-Encoder (ODLAE). Based on auto-encoder, considering reconstruction loss, we extract abstract hierarchical latent representations of instances; Based on predictive loss, we devise two fusion strategies: the output-level fusion strategy, which is obtained by fusing the classification results of encoder each hidden layer; and feature-level fusion strategy, which is leveraged self-attention mechanism to fusion every hidden layer output. Finally, in order to improve the robustness of the algorithm, we also try to utilize the denoising auto-encoder to yield hierarchical latent representations. Experimental results on different datasets are presented to verify the validity of our proposed algorithm (ODLAE) outperforms several baselines.

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。

↑