2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | MLSP-21.1 | ||
| Paper Title | DAG-GAN: CAUSAL STRUCTURE LEARNING WITH GENERATIVE ADVERSARIAL NETS | ||
| Authors | Yinghua Gao, Tsinghua University, China; Li Shen, Tencent AI Lab, China; Shu-Tao Xia, Tsinghua University, China | ||
| Session | MLSP-21: Generative Neural Networks | ||
| Location | Gather.Town | ||
| Session Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
| Presentation Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
| Presentation | Poster | ||
| Topic | Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Learning Directed Acyclic Graph (DAG) from purely observational data is a critical problem for causal inference. Most existing works tackle this problem by exploring gradient-based learning methods with a smooth characterization of acyclicity. A major shortcoming of current gradient-based works is that they independently optimize SEMs with a single sample and neglect the interactions between different samples. In this paper, we consider DAG structure learning from the perspective of distributional optimization and design an adversarial framework named DAG-GAN to detect the DAG structure from data. We theoretically analyze the Nash equilibrium property of DAG-GAN and propose a novel score function to exploit the interactions between different samples. In addition, extensive experiments are conducted to validate the efficiency of DAG-GAN against several state-of-the-art DAG learning methods. | ||