Jia Xiaodong, Jing Xiao-Yuan, Zhu Xiaoke, Chen Songcan, Du Bo, Cai Ziyun, He Zhenyu, Yue Dong
IEEE Trans Pattern Anal Mach Intell. 2021 Jul;43(7):2496-2509. doi: 10.1109/TPAMI.2020.2973634. Epub 2021 Jun 8.
Learning an expressive representation from multi-view data is a key step in various real-world applications. In this paper, we propose a semi-supervised multi-view deep discriminant representation learning (SMDDRL) approach. Unlike existing joint or alignment multi-view representation learning methods that cannot simultaneously utilize the consensus and complementary properties of multi-view data to learn inter-view shared and intra-view specific representations, SMDDRL comprehensively exploits the consensus and complementary properties as well as learns both shared and specific representations by employing the shared and specific representation learning network. Unlike existing shared and specific multi-view representation learning methods that ignore the redundancy problem in representation learning, SMDDRL incorporates the orthogonality and adversarial similarity constraints to reduce the redundancy of learned representations. Moreover, to exploit the information contained in unlabeled data, we design a semi-supervised learning framework by combining deep metric learning and density clustering. Experimental results on three typical multi-view learning tasks, i.e., webpage classification, image classification, and document classification demonstrate the effectiveness of the proposed approach.
从多视图数据中学习一种具有表现力的表示是各种实际应用中的关键一步。在本文中，我们提出了一种半监督多视图深度判别表示学习（SMDDRL）方法。与现有的联合或对齐多视图表示学习方法不同，这些方法不能同时利用多视图数据的一致性和互补性来学习视图间共享和视图内特定的表示，SMDDRL全面利用了一致性和互补性，并通过使用共享和特定表示学习网络来学习共享和特定表示。与现有的忽略表示学习中冗余问题的共享和特定多视图表示学习方法不同，SMDDRL纳入了正交性和对抗相似性约束以减少学习到的表示的冗余。此外，为了利用未标记数据中包含的信息，我们通过结合深度度量学习和密度聚类设计了一个半监督学习框架。在三个典型的多视图学习任务（即网页分类、图像分类和文档分类）上的实验结果证明了所提出方法的有效性。
