Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. As the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning researches, as well as to summarize and interpret the mechanisms and the strategies in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Different from previous surveys, this survey paper reviews over forty representative transfer learning approaches from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, twenty representative transfer learning models are used for experiments. The models are performed on three different datasets, i.e., Amazon Reviews, Reuters-21578, and Office-31. And the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.
The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function. It is easy for primary researchers to use this toolkit and to choose proper models for real-world applications. The toolkit is written in Python and distributed under MIT open source license. In this paper, the current state of this toolkit is described and the necessary environment setting and usage are introduced.
Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning. Apart from the huge consumption of manpower, computation and memory resources, most of these models seek point estimation of their parameters, and are prone to overfitting to small training data. This paper presents an adaptive kernel nonlinear max-margin multi-view learning model under the Bayesian framework. Specifically, we regularize the posterior of an efficient multi-view latent variable model by explicitly mapping the latent representations extracted from multiple data views to a random Fourier feature space where max-margin classification constraints are imposed. Assuming these random features are drawn from Dirichlet process Gaussian mixtures, we can adaptively learn shift-invariant kernels from data according to Bochners theorem. For inference, we employ the data augmentation idea for hinge loss, and design an efficient gradient-based MCMC sampler in the augmented space. Having no need to compute the Gram matrix, our algorithm scales linearly with the size of training set. Extensive experiments on real-world datasets demonstrate that our method has superior performance.
In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data. To simultaneously recognize new data categories and assign most appropriate category labels to the data actually from known categories, existing models assume the number of unknown new categories is pre-specified, though it is difficult to determine in advance. In this paper, we propose a Bayesian nonparametric topic model to automatically infer this number, based on the hierarchical Dirichlet process and the notion of latent Dirichlet allocation. Exact inference in our model is intractable, so we provide an efficient collapsed Gibbs sampling algorithm for approximate posterior inference. Extensive experiments on various text data sets show that: (a) compared with parametric approaches that use pre-specified true number of new categories, the proposed nonparametric approach can yield comparable performance; and (b) when the exact number of new categories is unavailable, i.e. the parametric approaches only have a rough idea about the new categories, our approach has evident performance advantages.
In this paper, a method for malfunctioning smart meter detection, based on Long Short-Term Memory (LSTM) and Temporal Phase Convolutional Neural Network (TPCNN), is proposed originally. This method is very useful for some developing countries where smart meters have not been popularized but in high demand. In addition, it is a new topic that people try to increase the service life span of smart meters to prevent unnecessary waste by detecting malfunctioning meters. We are the first people complete a combination of malfunctioning meters detection and prediction model based on deep learning methods. To the best our knowledge, our approach is the first method that achieves the malfunctioning meter detection of specific residential areas with their residents' data in practice. The procedure proposed creatively in this paper mainly consists of four components: data collecting and cleaning, prediction about electricity consumption based on LSTM, sliding window detection, and single user classification based on CNN. To make better classifying of malfunctioned user meters, we combine recurrence plots as image-input and combine them with sequence-input, which is the first work that applies one and two dimensions as two paths CNN's input for sequence data classification. Finally, many classical methods are compared with the method proposed in this paper. After comparison with classical methods, Elastic Net and Gradient Boosting Regression, the result shows that our method has higher accuracy. The average area under the Receiver Operating Characteristic (ROC) curve is 0.80 and the standard deviation is 0.04. The average area under the Precision-Recall Curve (PRC) is 0.84.
In machine learning, it is observed that probabilistic predictions sometimes disagree with averaged actual outcomes on certain subsets of data. This is also known as miscalibration that is responsible for unreliability and unfairness of practical machine learning systems. In this paper, we put forward an evaluation metric for calibration, coined field-level calibration error, that measures bias in predictions over the input fields that the decision maker concerns. We show that existing calibration methods perform poorly under our new metric. Specifically, after learning a calibration mapping over the validation dataset, existing methods have limited improvements in our error metric and completely fail to improve other non-calibration metrics such as the AUC score. We propose Neural Calibration, a new calibration method, which learns to calibrate by making full use of all input information over the validation set. We test our method on five large-scale real-world datasets. The results show that Neural Calibration significantly improves against uncalibrated predictions in all well-known metrics such as the negative log-likelihood, the Brier score, the AUC score, as well as our proposed field-level calibration error.
Recently, improving the relevance and diversity of dialogue system has attracted wide attention. For a post x, the corresponding response y is usually diverse in the real-world corpus, while the conventional encoder-decoder model tends to output the high-frequency (safe but trivial) responses and thus is difficult to handle the large number of responding styles. To address these issues, we propose the Atom Responding Machine (ARM), which is based on a proposed encoder-composer-decoder network trained by a teacher-student framework. To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms. In other words, even a little of atom-mechanisms can make a mickle of molecule-mechanisms. The experiments demonstrate diversity and quality of the responses generated by ARM. We also present generating process to show underlying interpretability for the result.
Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads with little logging data, which is known as the cold-start problem. In this paper, we aim to improve CTR predictions during both the cold-start phase and the warm-up phase when a new ad is added to the candidate pool. We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs. The proposed method trains an embedding generator for new ad IDs by making use of previously learned ads through gradient-based meta-learning. In other words, our method learns how to learn better embeddings. When a new ad comes, the trained generator initializes the embedding of its ID by feeding its contents and attributes. Next, the generated embedding can speed up the model fitting during the warm-up phase when a few labeled examples are available, compared to the existing initialization methods. Experimental results on three real-world datasets showed that Meta-Embedding can significantly improve both the cold-start and warm-up performances for six existing CTR prediction models, ranging from lightweight models such as Factorization Machines to complicated deep models such as PNN and DeepFM. All of the above apply to conversion rate (CVR) predictions as well.
Medical image segmentation has become an essential technique in clinical and research-oriented applications. Because manual segmentation methods are tedious, and fully automatic segmentation lacks the flexibility of human intervention or correction, semi-automatic methods have become the preferred type of medical image segmentation. We present a hybrid, semi-automatic segmentation method in 3D that integrates both region-based and boundary-based procedures. Our method differs from previous hybrid methods in that we perform region-based and boundary-based approaches separately, which allows for more efficient segmentation. A region-based technique is used to generate an initial seed contour that roughly represents the boundary of a target brain structure, alleviating the local minima problem in the subsequent model deformation phase. The contour is deformed under a unique force equation independent of image edges. Experiments on MRI data show that this method can achieve high accuracy and efficiency primarily due to the unique seed initialization technique.
Brain volume calculations are crucial in modern medical research, especially in the study of neurodevelopmental disorders. In this paper, we present an algorithm for calculating two classifications of brain volume, total brain volume (TBV) and intracranial volume (ICV). Our algorithm takes MRI data as input, performs several preprocessing and intermediate steps, and then returns each of the two calculated volumes. To simplify this process and make our algorithm publicly accessible to anyone, we have created a web-based interface that allows users to upload their own MRI data and calculate the TBV and ICV for the given data. This interface provides a simple and efficient method for calculating these two classifications of brain volume, and it also removes the need for the user to download or install any applications.