Inductive multi-task learning with multiple view data

By Jintao Zhang, Jun Huan. 2012

124 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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. Qiang Yang
2. Yu Zhang
3. 刘晗
4. Xiaotong Zhang
5. Xianchao Zhang
6. Mingxia Liu
7. Ying Wei
8. Jieping Ye

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Ying Wei
4. Jaime G. Carbonell
5. Jieping Ye
6. Mingxia Liu
7. Xiaotong Zhang
8. 刘晗

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “As a multi-task extension ofmulti-view learning,multi-taskmulti-view learning [80,81] hopes to exploit multiple multiview learning problems to improve the performance over eachmulti-view learning problemby leveraging useful information contained in related tasks.”
• A Survey on Multi-Task Learning (2017, methodology): “In [144], both a regularized MTL method [75] and the MTRL method are applied to each view of different tasks and different views in a task are expected to achieve an agreement on unlabeled data.”
• Block-Row Sparse Multiview Multilabel Learning for Image Classification (2016, methodology): “Zhang and Huan [46] used a co-regularization method to obtain functions consistent with each other on the unlabeled samples for different views.”
• Multi-view learning overview: Recent progress and new challenges (2017, background): “[22] Y. Li , F. Nie , H. Huang , J. Huang , Large-scale multi-view spectral clustering via bipartite graph, in: Proceedings of the 29th AAAI Conference on Artificial Intelligence, 2015, pp. 2750–2756 .”
• Transfer Knowledge between Cities (2016, background): “Besides, most multi-task multi-view learning algorithms transfer model parameters, thus ignore the di ff erences between tasks [33] or rely on enough labelled data in all tasks to learn the di ff erences [12, 17, 25].”
• Multi-Task Multi-View Clustering (2016, unknown): “Index Terms—Multi-task multi-view clustering, multi-task clustering, multi-view clustering, co-clustering Ç”
• Multi-Task Multiple Kernel Relationship Learning (2016, background): “elines. It is worth noting that the proposed multitask multiple kernel relationship learning can be readily applied for heterogeneous and multi-view data with no modification to the proposed framework [7,27]. The rest of the paper is organized as follows: we provide a brief overview of multitask mult”
• Attribute relation learning for zero-shot classification (2014, methodology): “More recently, this approach has been widely applied to many domains demonstrating its effectiveness, such as multi-task learning [44–48], transfer learning [49], multilabel learning [50,51], and multi-view learning [52].”
• Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis (2015, background): “Therefore, it is desirable to develop a multi-layer feature extractor [7], [32], [33], alleviating the tedious process of manual feature engineering and enhancing the representation power.”
• Multi-Task Multi-View Clustering for Non-Negative Data (2015, methodology): “For the other parameters, we apply grid searching [Zhang and Huan, 2012] to identify the optimal values.”