Multiple task transfer learning with small sample sizes
Multiple task transfer learning with small sample sizes
复制标题
DOI：
10.1007/s10115-015-0821-z
复制
发表时间：
2016-02-01
影响因子：
2.7
通讯作者：
Venkatesh, Svetha
中科院分区：
文献类型：
--
作者：
Saha, Budhaditya;Gupta, Sunil;Venkatesh, Svetha
预后，例如预测死亡率，在医学中很常见。当面对少量样本时，如在罕见的医疗条件下，这项任务具有挑战性。我们提出了一个小样本数据分类的框架。从概念上讲，我们的解决方案是多任务和迁移学习的混合，采用来自源任务的数据样本作为迁移学习，但在多任务学习中考虑所有任务。每个任务都通过直接增加来自其他任务的数据与其他相关任务联合建模。增强的程度取决于任务相关性，并直接从数据中估计。我们将该模型应用于三个不同的真实世界数据集（医疗数据，手写数字数据和人脸数据），并表明我们的方法优于几个最先进的多任务学习基线。我们扩展了在线多任务学习模型，其中模型参数在给定新数据或新任务的情况下逐步更新。我们的方法的新奇在于提供了一个混合多任务/迁移学习模型，以利用数据级的跨任务共享和联合参数学习。
Prognosis, such as predicting mortality, is common in medicine. When confronted with small numbers of samples, as in rare medical conditions, the task is challenging. We propose a framework for classification with data with small numbers of samples. Conceptually, our solution is a hybrid of multi-task and transfer learning, employing data samples from source tasks as in transfer learning, but considering all tasks together as in multi-task learning. Each task is modelled jointly with other related tasks by directly augmenting the data from other tasks. The degree of augmentation depends on the task relatedness and is estimated directly from the data. We apply the model on three diverse real-world data sets (healthcare data, handwritten digit data and face data) and show that our method outperforms several state-of-the-art multi-task learning baselines. We extend the model for online multi-task learning where the model parameters are incrementally updated given new data or new tasks. The novelty of our method lies in offering a hybrid multi-task/transfer learning model to exploit sharing across tasks at the data-level and joint parameter learning.