Multi-view learning overview: Recent progress and new challenges

By Jing Zhao, Xijiong Xie, Xin Xu, Shiliang Sun. 2017

935 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Francisco Herrera
2. Alberto Fernández
3. M. J. Jesús
4. Zeynep Akata
5. 刘晗
6. Xiaotong Zhang
7. Anjan Dutta
8. Xianchao Zhang

In Computational Mechanics

1. Nikola Konstantinov
2. Francesco Marcelloni
3. Francisco Herrera
4. Christoph H. Lampert
5. Céline Hudelot
6. Anjan Dutta
7. Xianchao Zhang
8. Yassine Ouali

In Computer Vision and Pattern Recognition

1. Zeynep Akata
2. Luc Van Gool
3. Jiebo Luo
4. Trevor Darrell
5. Bernt Schiele
6. Chen Change Loy
7. Dacheng Tao
8. Andrew Zisserman

In Representation & Self-Supervised Learning

1. Anjan Dutta
2. Christoph H. Lampert
3. Zeynep Akata
4. Alberto Fernández
5. Wenzhong Guo
6. Nikola Konstantinov
7. Xiaoqiang Yan
8. Eugene Yang

Citations in the corpus

• Hate speech detection: Challenges and solutions (2019, methodology): “It applies a multiple-view stacked Support Vector Machine (mSVM) [34].”
• Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to? (2019, background): “A topic that has gained much attention in the research community of data science is multi-view learning [55], where examples are described by multiple distinct feature sets.”
• Robust Learning from Untrusted Sources (2019, background): “Ro-bustness has also been explored in the context of multi-view learning, where data arrives from various feature extractors (Zhao et al., 2017; Xie, 2017; Zhang et al., 2017).”
• Deep multi-view learning methods: A review (2021, background): “MVL has penetrated a variety of learning methods [10, 26, 27, 28], such as dimensionality reduction [13], clustering analysis [29] and ensemble learning [30].”
• Multi-Task Clustering with Model Relation Learning (2018, methodology): “Multi-View Learning: Different from multi-task learning which deals with the data from multiple tasks, multi-view learning [Zhao et al. , 2017] deals with the data which have the features from different views.”
• Learning Robust Representations via Multi-View Information Bottleneck (2020, methodology): “To do this, we rely on a basic assumption of the multi-view literature – that each view provides the same task-relevant information (Zhao et al., 2017).”
• Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, background): “Multi-view learning, also known as data fusion, aims to integrate multiple data information from different views to improve the performance of learning tasks [23, 60].”
• A Survey on Multi-View Clustering (2017, neutral): “The existence of such multi-view data raised the interest of multi-view learning [2], [3], [4], which has been extensively studied in the semi-supervised learning setting.”
• Deep Multimodal Representation Learning: A Survey (2019, background): “[17] mainly focuses on conventional methods.”
• Semi-Supervised Semantic Segmentation With Cross-Consistency Training (2020, background): “Our work is also loosely related to Multi-View learning [60] and Cross-View training [9], where each input to the auxiliary decoders can be view as an alternate, but corrupt representation of the unlabeled examples.”