A Unified Active Learning Framework for Biomedical Relation Extraction

Supervised machine learning methods have been employed with great success in the task of biomedical relation extraction.However,existing methods are not practical enough,since manual construction of large training data is very expensive.Therefore,active learning is urgently needed for designing practical relation extraction methods with little human effort.In this paper,we describe a unified active learning framework.Particularly,our framework systematically addresses some practical issues during active learning process,including a strategy for selecting informative data,a data diversity selection algorithm,an active feature acquisition method,and an informative feature selection algorithm,in order to meet the challenges due to the immense amount of complex and diverse biomedical text.The framework is evaluated on proteinprotein interaction(PPI) extraction and is shown to achieve promising results with a significant reduction in editorial effort and labeling time.     

Incremental Multi-Label Learning with Active Queries

In multi-label learning,it is rather expensive to label instances since they are simultaneously associated with multiple labels.Therefore,active learning,which reduces the labeling cost by actively querying the labels of the most valuable data,becomes particularly important for multi-label learning.A good multi-label active learning algorithm usually consists of two crucial elements:a reasonable criterion to evaluate the gain of querying the label for an instance,and an effective classification model,based on whose prediction the criterion can be accurately computed.In this paper,we first introduce an effective multi-label classification model by combining label ranking with threshold learning,which is incrementally trained to avoid retraining from scratch after every query.Based on this model,we then propose to exploit both uncertainty and diversity in the instance space as well as the label space,and actively query the instance-label pairs which can improve the classification model most.Extensive experiments on 20 datasets demonstrate the superiority of the proposed approach to state-of-the-art methods.     

Software Defect Detection with R<Emphasis Type="SmallCaps">ocus</Emphasis>

Software defect detection aims to automatically identify defective software modules for efficient software test in order to improve the quality of a software system.Although many machine learning methods have been successfully applied to the task,most of them fail to consider two practical yet important issues in software defect detection.First,it is rather difficult to collect a large amount of labeled training data for learning a well-performing model;second,in a software system there are usually much fewer defective modules than defect-free modules,so learning would have to be conducted over an imbalanced data set.In this paper,we address these two practical issues simultaneously by proposing a novel semi-supervised learning approach named Rocus.This method exploits the abundant unlabeled examples to improve the detection accuracy,as well as employs under-sampling to tackle the class-imbalance problem in the learning process.Experimental results of real-world software defect detection tasks show that Rocus is effective for software defect detection.Its performance is better than a semi-supervised learning method that ignores the class-imbalance nature of the task and a class-imbalance learning method that does not make effective use of unlabeled data.     

A Kernel Approach to Multi-Task Learning with Task-Specific Kernels

Several kernel-based methods for multi-task learning have been proposed,which leverage relations among tasks as regularization to enhance the overall learning accuracies.These methods assume that the tasks share the same kernel,which could limit their applications because in practice different tasks may need different kernels.The main challenge of introducing multiple kernels into multiple tasks is that models from different reproducing kernel Hilbert spaces(RKHSs) are not comparable,making it difficult to exploit relations among tasks.This paper addresses the challenge by formalizing the problem in the square integrable space(SIS).Specially,it proposes a kernel-based method which makes use of a regularization term defined in SIS to represent task relations.We prove a new representer theorem for the proposed approach in SIS.We further derive a practical method for solving the learning problem and conduct consistency analysis of the method.We discuss the relationship between our method and an existing method.We also give an SVM(support vector machine)based implementation of our method for multi-label classification.Experiments on an artificial example and two real-world datasets show that the proposed method performs better than the existing method.     

Class conditional distribution alignment for domain adaptation

In this paper, we study the problem of domain adaptation, which is a crucial ingredient in transfer learning with two domains, that is, the source domain with labeled data and the target domain with none or few labels. Domain adaptation aims to extract knowledge from the source domain to improve the performance of the learning task in the target domain. A popular approach to handle this problem is via adversarial training, which is explained by the $\mathcal H \Delta \mathcal H$-distance theory. However, traditional adversarial network architectures just align the marginal feature distribution in the feature space. The alignment of class condition distribution is not guaranteed. Therefore, we proposed a novel method based on pseudo labels and the cluster assumption to avoid the incorrect class alignment in the feature space. The experiments demonstrate that our framework improves the accuracy on typical transfer learning tasks.     

Sequencing of multi‑robot behaviors using reinforcement learning

Given a collection of parameterized multi-robot controllers associated with individual behaviors designed for particular tasks, this paper considers the problem of how to sequence and instantiate the behaviors for the purpose of completing a more complex, overarching mission. In addition, uncertainties about the environment or even the mission specifications may require the robots to learn, in a cooperative manner, how best to sequence the behaviors. In this paper, we approach this problem by using reinforcement learning to approximate the solution to the computationally intractable sequencing problem, combined with an online gradient descent approach to selecting the individual behavior parameters, while the transitions among behaviors are triggered automatically when the behaviors have reached a desired performance level relative to a task performance cost. To illustrate the effectiveness of the proposed method, it is implemented on a team of differential-drive robots for solving two different missions, namely, convoy protection and object manipulation.     

A Machine Learning Framework with Feature Selection for Floorplan Acceleration in IC Physical Design

Floorplan is an important process whose quality determines the timing closure in integrated circuit(IC)physical design.And generating a floorplan with satisfying timing result is time-consuming because much time is spent on the generation-evaluation iteration.Applying machine learning to the floorplan stage is a potential method to accelerate the floorplan iteration.However,there exist two challenges which are selecting proper features and achieving a satisfying model accuracy.In this paper,we propose a machine learning framework for floorplan acceleration with feature selection and model stacking to cope with the challenges,targeting to reduce time and effort in integrated circuit physical design.Specifically,the proposed framework supports predicting post-route slack of static random-access memory(SRAM)in the early floorplan stage.Firstly,we introduce a feature selection method to rank and select important features.Considering both feature importance and model accuracy,we reduce the number of features from 27 to 15(44%reduction),which can simplify the dataset and help educate novice designers.Then,we build a stacking model by combining different kinds of models to improve accuracy.In 28 nm technology,we achieve the mean absolute error of slacks less than 23.03 ps and effectively accelerate the floorplan process by reducing evaluation time from 8 hours to less than 60 seconds.Based on our proposed framework,we can do design space exploration for thousands of locations of SRAM instances in few seconds,much more quickly than the traditional approach.In practical application,we improve the slacks of SRAMs more than 75.5 ps(177%improvement)on average than the initial design.     

Deep Imitation Learning for Autonomous Vehicles Based on Convolutional Neural Networks

Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.     

A convergence algorithm for graph co-regularized transfer learning

Transfer learning is an important technology in addressing the problem that labeled data in a target domain are difficult to collect using extensive labeled data from the source domain. Recently,an algorithm named graph co-regularized transfer learning(GTL) has shown a competitive performance in transfer learning. However, its convergence is affected by the used approximate scheme, degenerating learned results. In this paper, after analyzing convergence conditions, we propose a novel update rule...     

Hybrid Two-Phase Task Allocation for Mobile Crowd Sensing

As a result of the popularity of mobile devices,Mobile Crowd Sensing (MCS) has attracted a lot of attention. Task allocation is a significant problem in MCS. Most previous studies mainly focused on stationary spatial tasks while neglecting the changes of tasks and workers. In this paper,the proposed hybrid two-phase task allocation algorithm considers heterogeneous tasks and diverse workers.For heterogeneous tasks,there are different start times and deadlines. In each round,the tasks are divided into urgent and non-urgent tasks. The diverse workers are classified into opportunistic and participatory workers.The former complete tasks on their way,so they only receive a fixed payment as employment compensation,while the latter commute a certain distance that a distance fee is paid to complete the tasks in each round as needed apart from basic employment compensation. The task allocation stage is divided into multiple rounds consisting of the opportunistic worker phase and the participatory worker phase. At the start of each round,the hiring of opportunistic workers is considered because they cost less to complete each task. The Poisson distribution is used to predict the location that the workers are going to visit,and greedily choose the ones with high utility. For participatory workers,the urgent tasks are clustered by employing hierarchical clustering after selecting the tasks from the uncompleted task set.After completing the above steps,the tasks are assigned to participatory workers by extending the Kuhn-Munkres (KM) algorithm.The rest of the uncompleted tasks are non-urgent tasks which are added to the task set for the next round.Experiments are conducted based on a real dataset,Brightkite,and three typical baseline methods are selected for comparison. Experimental results show that the proposed algorithm has better performance in terms of total cost as well as efficiency under the constraint that all tasks are completed.     

Query by diverse committee in transfer active learning

Transfer active learning, which is an emerging learning paradigm, aims to actively select informative instances with the aid of transferred knowledge from related tasks. Recently, several studies have addressed this problem. However, how to handle the distributional differences between the source and target domains remains an open problem. In this paper, a novel transfer active learning algorithm is proposed, inspired by the classical query by committee algorithm. Diverse committee members from both domains are maintained to improve the classification accuracy and a mechanism is included to evaluate each member during the iterations. Extensive experiments on both synthetic and real datasets show that our algorithm performs better and is also more robust than the state-of-the-art methods.     

基于压缩编码的迁移学习算法研究

在生产实际中,一个新的任务通常和已有任务存在一定的联系。迁移学习方法可以将已有数据集中的有用信息,迁移到新的任务,以减少重新建模过程中大量的时间和费用消耗。然而,由于任务之间的分布差异,在异构环境下如何避免负面迁移问题,仍未得到有效的解决。除了要衡量数据间的相似性,还需要衡量实例间的相关性,而大多数传统方法仅在一个层面进行操作。提出了基于压缩编码的迁移学习方法（TLCC）,建立了两个层面的算法模型,具体来说,在数据层面,数据间的相似性可以表示为超平面分类器的编码长度,而在实例层面,通过进一步挑选出有价值的实例进行迁移,提升算法性能,避免负面迁移的发生。实验结果表明,提出的算法相比其他算法具有明显的优势,在噪声环境下也有较高的准确度。     

Multi-label active learning by model guided distribution matching

Multi-label learning is an effective framework for learning with objects that have multiple semantic labels, and has been successfully applied into many real-world tasks. In contrast with traditional single-label learning, the cost of labeling a multi-label example is rather high, thus it becomes an important task to train an effectivemulti-label learning model with as few labeled examples as possible. Active learning, which actively selects the most valuable data to query their labels, is the most important approach to reduce labeling cost. In this paper, we propose a novel approach MADM for batch mode multi-label active learning. On one hand, MADM exploits representativeness and diversity in both the feature and label space by matching the distribution between labeled and unlabeled data. On the other hand, it tends to query predicted positive instances, which are expected to be more informative than negative ones. Experiments on benchmark datasets demonstrate that the proposed approach can reduce the labeling cost significantly.     

Active transfer learning of matching query results across multiple sources

Entity resolution (ER) is the problem of identifying and grouping different manifestations of the same real world object. Algorithmic approaches have been developed where most tasks offer superior performance under supervised learning. However, the prohibitive cost of labeling training data is still a huge obstacle for detecting duplicate query records from online sources. Furthermore, the unique combinations of noisy data with missing elements make ER tasks more challenging. To address this, transfer learning has been adopted to adaptively share learned common structures of similarity scoring problems between multiple sources. Although such techniques reduce the labeling cost so that it is linear with respect to the number of sources, its random sampling strategy is not successful enough to handle the ordinary sample imbalance problem. In this paper, we present a novel multi-source active transfer learning framework to jointly select fewer data instances from all sources to train classifiers with constant precision/recall. The intuition behind our approach is to actively label the most informative samples while adaptively transferring collective knowledge between sources. In this way, the classifiers that are learned can be both label-economical and flexible even for imbalanced or quality diverse sources. We compare our method with the state-of-the-art approaches on real-word datasets. Our experimental results demonstrate that our active transfer learning algorithm can achieve impressive performance with far fewer labeled samples for record matching with numerous and varied sources.     

主动学习的多标签图像在线分类

目的在多标签有监督学习框架中,构建具有较强泛化性能的分类器需要大量已标注训练样本,而实际应用中已标注样本少且获取代价十分昂贵。针对多标签图像分类中已标注样本数量不足和分类器再学习效率低的问题,提出一种结合主动学习的多标签图像在线分类算法。方法基于min-max理论,采用查询最具代表性和最具信息量的样本挑选策略主动地选择待标注样本,且基于KKT(Karush-Kuhn-Tucker)条件在线地更新多标签图像分类器。结果在4个公开的数据集上,采用4种多标签分类评价指标对本文算法进行评估。实验结果表明,本文采用的样本挑选方法比随机挑选样本方法和基于间隔的采样方法均占据明显优势;当分类器达到相同或相近的分类准确度时,利用本文的样本挑选策略选择的待标注样本数目要明显少于采用随机挑选样本方法和基于间隔的采样方法所需查询的样本数。结论本文算法一方面可以减少获取已标注样本所需的人工标注代价;另一方面也避免了传统的分类器重新训练时利用所有数据所产生的学习效率低下的问题,达到了当新数据到来时可实时更新分类器的目的。     

Batch Mode Active Learning with Applications to Text Categorization and Image Retrieval

Most machine learning tasks in data classification and information retrieval require manually labeled data examples in the training stage. The goal of active learning is to select the most informative examples for manual labeling in these learning tasks. Most of the previous studies in active learning have focused on selecting a single unlabeled example in each iteration. This could be inefficient, since the classification model has to be retrained for every acquired labeled example. It is also inappropriate for the setup of information retrieval tasks where the user's relevance feedback is often provided for the top K retrieved items. In this paper, we present a framework for batch mode active learning, which selects a number of informative examples for manual labeling in each iteration. The key feature of batch mode active learning is to reduce the redundancy among the selected examples such that each example provides unique information for model updating. To this end, we employ the Fisher information matrix as the measurement of model uncertainty, and choose the set of unlabeled examples that can efficiently reduce the Fisher information of the classification model. We apply our batch mode active learning framework to both text categorization and image retrieval. Promising results show that our algorithms are significantly more effective than the active learning approaches that select unlabeled examples based only on their informativeness for the classification model.     

一种处理多类分类问题的强化支持向量机方法

提出了一种强化支持向量机方法,将支持向量机与强化学习结合,逐步对未知类别标记样本进行访问,根据对该样本分类结果正确与否的评价标记访问点的类别,并对当前的分类器进行更新,给出了更新分类器的规则。对模拟数据和真实数据分别进行了实验,表明该方法在保证分类精度的同时,大大降低了对已知类别标记的训练样本的数量要求,是处理已知类别标记样本获取困难的多类分类问题的一种有效的方法。     

基于迁移学习的文本共情预测

由于缺乏足够的训练数据,文本共情预测的进展一直都较为缓慢;而与之相关的文本情感极性分类任务则存在大量有标签的训练样本。由于文本共情预测与文本情感极性分类两个任务间存在较大相关性,因此提出了一种基于迁移学习的文本共情预测方法,该方法可从情感极性分类任务中学习到可迁移的公共特征,并通过学习到的公共特征辅助文本共情预测任务。首先通过一个注意力机制对两个任务间的公私有特征进行动态加权融合;其次为了消除两个任务间的数据集领域差异,通过一种对抗学习策略来区分两个任务间的领域独有特征与领域公共特征;最后提出了一种Hinge?loss约束策略,使共同特征对不同的目标标签具有通用性,而私有特征对不同的目标标签具有独有性。在两个基准数据集上的实验结果表明,相较于对比的迁移学习方法,所提方法的皮尔逊相关系数（PCC）和决定系数（R²）更高,均方误差（MSE）更小,充分说明了所提方法的有效性。     

自适应主动半监督学习方法

主动学习从大量无标记样本中挑选样本交给专家标记.现有的批抽样主动学习算法主要受3个限制：（1）一些主动学习方法基于单选择准则或对数据、模型设定假设,这类方法很难找到既有不确定性又有代表性的未标记样本;（2）现有批抽样主动学习方法的性能很大程度上依赖于样本之间相似性度量的准确性,例如预定义函数或差异性衡量;（3）噪声标签问题一直影响批抽样主动学习算法的性能.提出一种基于深度学习批抽样的主动学习方法.通过深度神经网络生成标记和未标记样本的学习表示和采用标签循环模式,使得标记样本与未标记样本建立联系,再回到相同标签的标记样本.这样同时考虑了样本的不确定性和代表性,并且算法对噪声标签具有鲁棒性.在提出的批抽样主动学习方法中,算法使用的子模块函数确保选择的样本集合具有多样性.此外,自适应参数的优化,使得主动学习算法可以自动平衡样本的不确定性和代表性.将提出的主动学习方法应用到半监督分类和半监督聚类中,实验结果表明,所提出的主动学习方法的性能优于现有的一些先进的方法.