arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06170cs.LG
收藏

深度部分多视图学习

Deep Partial Multi-View Learning

College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);Inception Institute of Artificial Intelligence(起源人工智能研究院)

Changqing Zhang, Yajie Cui, Zongbo Han, Joey Tianyi Zhou, Huazhu Fu, Qinghua Hu

摘要:

虽然多视图学习在过去的几十年里取得了显著的进展,但由于难以建模不同视图之间的复杂相关性,特别是在视图丢失的情况下,它仍然具有挑战性。为了解决这个问题,我们提出了一个新的框架称为跨部分多视图网络(CPM网),其目的是充分和灵活地利用多个部分视图。我们首先提供了一个正式的多视图表示的完整性和通用性的定义,然后从理论上证明了学习的潜在表示的通用性。为了完整性,学习潜在的多视图表示的任务被专门翻译成一个退化过程,通过模仿数据传输,使得不同视图之间的一致性和互补性之间的最佳权衡可以隐含地实现。配备对抗策略,我们的模型稳定地估算缺失的视图,将每个样本的所有视图的信息编码为潜在表示,以进一步增强完整性。此外,一个非参数的分类损失被引入到产生结构化的表示,并防止过填充,这赋予算法有前途的泛化下的视图丢失的情况下。大量的实验结果验证了我们的算法在分类,表示学习和数据填补现有的艺术状态的有效性。

英文摘要:

Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To address the challenge, we propose a novel framework termed Cross Partial Multi-View Networks (CPM-Nets), which aims to fully and flflexibly take advantage of multiple partial views. We fifirst provide a formal defifinition of completeness and versatility for multi-view representation and then theoretically prove the versatility of the learned latent representations. For completeness, the task of learning latent multi-view representation is specififically translated to a degradation process by mimicking data transmission, such that the optimal tradeoff between consistency and complementarity across different views can be implicitly achieved. Equipped with adversarial strategy, our model stably imputes missing views, encoding information from all views for each sample to be encoded into latent representation to further enhance the completeness. Furthermore, a nonparametric classifification loss is introduced to produce structured representations and prevent overfifitting, which endows the algorithm with promising generalization under view-missing cases. Extensive experimental results validate the effectiveness of our algorithm over existing state of the arts for classifification, representation learning and data imputation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑