|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Inductive transfer learning for unlabeled target-domain via hybrid regularization显示文摘Recent years have witnessed an increasing interest in transfer learning. This paper deals with the classification problem that the target-domain with a different distribution from the source-domain is totally unlabeled, and aims to build an inductive model for unseen data. Firstly, we analyze the problem of class ratio drift in the previous work of transductive transfer learning, and propose to use a normalization method to move towards the desired class ratio. Furthermore, we develop a hybrid regularization framework for inductive transfer learning. It considers three factors, including the distribution geometry of the target-domain by manifold regularization, the entropy value of prediction probability by entropy regularization, and the class prior by expectation regularization. This framework is used to adapt the inductive model learnt from the source-domain to the target-domain. Finally, the experiments on the real-world text data show the effectiveness of our inductive method of transfer learning. Meanwhile, it can handle unseen test points. | ZHUANG FuZhen LUO Ping HE Qing SHI ZhongZhi | 2009 | Chinese Science Bulletin2009，54，14： | 3 |
| 2 | Potential Off-Grid User Prediction System Based on Spark显示文摘With the increasingly fierce competition among communication operators,it is more and more important to make an accurate prediction of potential off grid users.To solve the above problem,it is inevitable to consider the effectiveness of learning algo rithms,the efficiency of data processing,and other factors.Therefore,in this paper,we,from the practical application point of view,propose a potential customer off grid predic tion system based on Spark,including data pre processing,feature selection,model build ing,and effective display.Furthermore,in the research of off grid system,we use the Spark parallel framework to improve the gcForest algorithm which is a novel decision tree ensemble approach.The new parallel gcForest algorithm can be used to solve practical problems,such as the off grid prediction problem.Experiments on two real world datasets demonstrate that the proposed prediction system can handle large scale data for the off grid user prediction problem and the proposed parallel gcForest can achieve satisfying per formance. | LI Xuebing SUN Ying ZHUANG Fuzhen HE Jia ZHANG Zhao ZHU Shijun HE Qing | 2019 | ZTE Communications2019，17，2： | 2 |
| 3 | Energy model for rumor propagation on social networks 显示文摘 | Han Shuo Zhuang Fuzhen He Qing | 2014 | Physica A: Statistical Me- chanics and its Applications2014，394，15： | 1 |
| 4 | Mining dis?tinction and commonality across multiple domains using gen?erative model for text classification显示文摘 | Zhuang Fuzhen Luo Ping Shen Zhiyong | 2012 | IEEE Transactions on Knowledge and Data Engineering2012，24，11： | 1 |
| 5 | Energy model for rumor propagation on social networks显示文摘 | Shuo Han Fuzhen Zhuang Qing He Zhongzhi Shi Xiang Ao | 2014 | Physica A: Statistical Mechanics and its Applica- tions2014，，394： | 1 |
| 6 | Parallel Web Mining System Based on Cloud Platform显示文摘Traditional machine-learning algorithms are struggling to handle the exceedingly large amount of data being generated by the internet. In real-world applications, there is an urgent need for machine-learning algorithms to be able to handle large-scale, high-dimensional text data. Cloud computing involves the delivery of computing and storage as a service to a heterogeneous community of recipients. Recently, it has aroused much interest in industry and academia. Most previous works on cloud platforms only focus on the parallel algorithms for structured data. In this paper, we focus on the parallel implementation of web-mining algorithms and develop a parallel web-mining system that includes parallel web crawler; parallel text extract, transform and load (ETL) and modeling; and parallel text mining and application subsystems. The complete system enables variable real-world web-mining applications for mass data. | Shengmei Luo Qing He Lixia Liu Xiang Ao Ning Li Fuzhen Zhuang | 2012 | ZTE Communications2012，10，4： | 1 |
| 7 | Particle swarm optimization using dimension selection methods显示文摘 | Xin Jin Yongquan Liang Dongping Tian Fuzhen Zhuang | 2013 | Applied Mathematics and Computation2013，，10： | 1 |
| 8 | Bayesian dual neural networks for recommendation显示文摘Most traditional collaborative filtering(CF)methods only use the user-item rating matrix to make recommendations,which usually suffer from cold-start and sparsity problems.To address these problems,on the one hand,some CF methods are proposed to incorporate auxiliary information such as user/item profiles;on the other hand,deep neural networks,which have powerful ability in learning effective representations,have achieved great success in recommender systems.However,these neural network based recommendation methods rarely consider the uncertainty of weights in the network and only obtain point estimates of the weights.Therefore,they maybe lack of calibrated probabilistic predictions and make overly confident decisions.To this end,we propose a new Bayesian dual neural network framework,named BDNet,to incorporate auxiliary information for recommendation.Specifically,we design two neural networks,one is to learn a common low dimensional space for users and items from the rating matrix,and another one is to project the attributes of users and items into another shared latent space.After that,the outputs of these two neural networks are combined to produce the final prediction.Furthermore,we introduce the uncertainty to all weights which are represented by probability distributions in our neural networks to make calibrated probabilistic predictions.Extensive experiments on real-world data sets are conducted to demonstrate the superiority of our model over various kinds of competitors. | Jia HE Fuzhen ZHUANG Yanchi LIU Qing HE Fen LIN | 2019 | Frontiers of Computer Science2019，13，6： | 1 |
| 9 | Combat data shift in few-shot learning with knowledge graph显示文摘Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance. | Yongchun ZHU Fuzhen ZHUANG Xiangliang ZHANG Zhiyuan QI Zhiping SHI Juan CAO Qing HE | 2023 | Frontiers of Computer Science2023，17，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员