提出协方差损失函数，提升模型对噪声和缺失依赖的鲁棒性。
Conditional Temporal Neural Processes with Covariance Loss
- 设计协方差损失，通过目标变量依赖关系增强模型表达
- 在真实数据集上验证，显著提升对噪声观测的鲁棒性
- 适用于多种神经网络，尤其适合依赖关系复杂的建模任务
我们提出一种新型损失函数——协方差损失，其在概念上等价于条件神经过程，并具有正则化形式，可适配多种神经网络。该损失使输入到输出的映射高度依赖目标变量之间的关系，以及输入与输出的均值激活和均值依赖结构。这一特性使训练后的神经网络对噪声观测更具鲁棒性，并能从先验信息中恢复缺失的依赖关系。为验证所提损失的有效性，我们在多个真实世界数据集上使用先进模型进行了广泛实验，并讨论了协方差损失的优势与局限。
原文摘要 · Abstract (English)
We introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many kinds of neural networks. With the proposed loss, mappings from input variables to target variables are highly affected by dependencies of target variables as well as mean activation and mean dependencies of input and target variables. This nature enables the resulting neural networks to become more robust to noisy observations and recapture missing dependencies from prior information. In order to show the validity of the proposed loss, we conduct extensive sets of experiments on real-world datasets with state-of-the-art models and discuss the benefits and drawbacks of the proposed Covariance Loss.
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。