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

01/01/2022
by   Jian-wei Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/07/2022

mulEEG: A Multi-View Representation Learning on EEG Signals

Modeling effective representations using multiple views that positively ...
research
10/14/2019

Mixed Pooling Multi-View Attention Autoencoder for Representation Learning in Healthcare

Distributed representations have been used to support downstream tasks i...
research
01/01/2023

Multi-View MOOC Quality Evaluation via Information-Aware Graph Representation Learning

In this paper, we study the problem of MOOC quality evaluation which is ...
research
09/14/2020

Collaborative Attention Mechanism for Multi-View Action Recognition

Multi-view action recognition (MVAR) leverages complementary temporal in...
research
08/09/2021

Multi-View TRGRU: Transformer based Spatiotemporal Model for Short-Term Metro Origin-Destination Matrix Prediction

Accurate prediction of short-term OD Matrix (i.e. the distribution of pa...
research
06/23/2021

LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction

Most modern deep learning-based multi-view 3D reconstruction techniques ...
research
12/10/2022

Progressive Multi-view Human Mesh Recovery with Self-Supervision

To date, little attention has been given to multi-view 3D human mesh est...

Please sign up or login with your details

Forgot password? Click here to reset