學(xué)術(shù)空間 / 論文 / 會(huì)議論文
Deep Multi-Task Learning with Adversarial-and-Cooperative Nets
收藏
| 作 者 | Pei Yang , Qi Tan , Jieping Ye , Hanghang Tong , Jingrui He |
| 會(huì)議名稱 | The 2019 International Joint Conference on Artificial Intelligence (IJCAI 2019). |
| 發(fā)表日期 | 2019 年 08 月 |
| 摘 要 |
In this paper, we propose a deep multi-Task learning model based on Adversarial-and-COoperative nets (TACO). The goal is to use an adversarial-and-cooperative strategy to decouple the task-common and task-specific knowledge, facilitating the fine-grained knowledge sharing among tasks. TACO accommodates multiple game players, i.e., feature extractors, domain discriminator, and tri-classifiers. They play the MinMax games adversarially and cooperatively to distill the task-common and task-specific features, while respecting their discriminative structures. Moreover, it adopts a divide-and-combine strategy to leverage the decoupled multi-view information to further improve the generalization performance of the model. The experimental results show that our proposed method significantly outperforms the state-of-the-art algorithms on the benchmark datasets in both multi-task learning and semi-supervised domain adaptation scenarios. |
| 附 件 |
