arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.00168cs.LGcs.CV
收藏

多样性促进互补的自注意力多视角表示学习

Self-attention Multi-view Representation Learning with Diversity-promoting Complementarity

School of Information Science and Engineering, Northeastern University(东北大学信息科学与工程学院);Harbin Institute of Technology(哈尔滨工业大学)

Jian-wei Liu, Xi-hao Ding, Run-kun Lu, Xionglin Luo

摘要:

多视图学习试图通过利用多视图数据之间的一致性和/或互补性来生成具有更好性能的模型。然而,在互补性方面,大多数现有的方法只能找到具有单一互补性的表示,而不是具有多样性的互补信息。在本文中,为了同时利用互补性和一致性,充分发挥深度学习在多视图表示学习中把握多样性促进互补性的潜力,我们提出了一种新的有监督多视图表示学习算法,称为具有多样性促进互补性的自注意力多视图网络(SAMVDPC),它通过一组编码器利用一致性,使用自注意力来寻找需要多样性的补充信息。在8个真实数据集上进行的大量实验证明了该方法的有效性,并显示了其优于仅考虑单一互补信息的几种基线方法的优势。

英文摘要:

Multi-view learning attempts to generate a model with a better performance by exploiting the consensus and/or complementarity among multi-view data. However, in terms of complementarity, most existing approaches only can find representations with single complementarity rather than complementary information with diversity. In this paper, to utilize both complementarity and consistency simultaneously, give free rein to the potential of deep learning in grasping diversity-promoting complementarity for multi-view representation learning, we propose a novel supervised multi-view representation learning algorithm, called Self-Attention Multi-View network with Diversity-Promoting Complementarity (SAMVDPC), which exploits the consistency by a group of encoders, uses self-attention to find complementary information entailing diversity. Extensive experiments conducted on eight real-world datasets have demonstrated the effectiveness of our proposed method, and show its superiority over several baseline methods, which only consider single complementary information.

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。

↑