青岛科技大学  English 
赵文仓
赞  

教师拼音名称:zhaowencang

手机版

访问量:

最后更新时间:..

A Causality-Aware Perspective on Domain Generalization via Domain Intervention

关键字:

摘要:Most mainstream statistical models will achieve poor performance in Out-Of-Distribution (OOD) generalization. This is because these models tend to learn the spurious correlation between data and will collapse when the domain shift exists. If we want artificial intelligence (AI) to make great strides in real life, the current focus needs to be shifted to the OOD problem of deep learning models to explore the generalization ability under unknown environments. Domain generalization (DG) focusing on OOD generalization is proposed, which is able to transfer the knowledge extracted from multiple source domains to the unseen target domain. We are inspired by intuitive thinking about human intelligence relying on causality. Unlike relying on plain probability correlations, we apply a novel causal perspective to DG, which can improve the OOD generalization ability of the trained model by mining the invariant causal mechanism. Firstly, we construct the inclusive causal graph for most DG tasks through stepwise causal analysis based on the data generation process in the natural environment and introduce the reasonable Structural Causal Model (SCM). Secondly, based on counterfactual inference, causal semantic representation learning with domain intervention (CSRDN) is proposed to train a robust model. In this regard, we generate counterfactual representations for different domain interventions, which can help the model learn causal semantics and develop generalization capacity. At the same time, we seek the Pareto optimal solution in the optimization process based on the loss function to obtain a more advanced training model. Extensive experimental results of Rotated MNIST and PACS as well as VLCS datasets verify the effectiveness of the proposed CSRDN. The proposed method can integrate causal inference into domain generalization by enhancing interpretability and applicability and brings a boost to challenging OOD generalization problems.

卷号:13

期号:10

是否译文:

崂山校区 - 山东省青岛市松岭路99号   
四方校区 - 山东省青岛市郑州路53号   
中德国际合作区(中德校区) - 山东省青岛市西海岸新区团结路3698号
高密校区 - 山东省高密市杏坛西街1号   
济南校区 - 山东省济南市文化东路80号©2015 青岛科技大学    
管理员邮箱:master@qust.edu.cn