• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Continual Multiview Task Learning via Deep Matrix Factorization
【24h】

Continual Multiview Task Learning via Deep Matrix Factorization

机译：通过深矩阵分解，继续多视图任务学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.
机译：最先进的多任务多视图（MTMV）学习解决方案，其中多个任务通过多个共享特征视图彼此相关。然而，在许多现实世界场景中，多视图任务的序列来看，通过MTMV模型再培训先前任务的较高的存储需求和计算成本已经为这一终身学习场景呈现了一个强大的挑战。为了解决这一挑战，在本文中，我们提出了一种新的持续多视图任务学习模型，可以在统一的框架中集成深矩阵分解和稀疏子空间学习，这些框架被称为深度连续的多视图任务学习（DCMVTL）。更具体地，作为一个新的多视图任务到达，DCMVTL首先采用深度矩阵分解技术来捕获这种新的多视图任务的隐藏和分层表示，同时以完整的方式累积新的多视图知识。然后，采用稀疏子空间学习模型用于每个层的提取因子，进一步通过自表现约束揭示互联相关性。对于型号优化，我们在新的多视图任务来上，我们推出了一般的多视图学习制定，并应用交替的最小化策略来实现终身学习。基准数据集的广泛实验展示了我们提出的DCMVTL模型的有效性与现有的最先进的MTMV和Lifelong Multiview任务学习模型相比。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号