检索结果-南通市图书馆

Rts: learning robustly from time series data with noisy label

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第6期18卷 186332-186332页

作者： ZHOU Zhi JIN Yi-Xuan Li Yu-Feng national key laboratory for novel software technology Nanjing University

Significant progress has been made in machine learning with large amounts of clean labels and static data. However, in many real-world applications, the data often changes with time and it is difficult to obtain massive clean annotations, that is, noisy labels and time series are faced simultaneously. For example, in product-buyer evaluation, each sample records the daily time behavior of users, but the long transaction period brings difficulties to analysis, and salespeople often erroneously annotate the user’s purchase behavior. Such a novel setting, to our best knowledge, has not been thoroughly studied yet, and there is still a lack of effective machine learning methods. In this paper, we present a systematic approach RTS both theoretically and empirically, consisting of two components, Noise-Tolerant Time Series Representation and Purified Oversampling Learning. Specifically, we propose reducing label noise’s destructive impact to obtain robust feature representations and potential clean samples. Then, a novel learning method based on the purified data and time series oversampling is adopted to train an unbiased model. Theoretical analysis proves that our proposal can improve the quality of the noisy data set. Empirical experiments on diverse tasks, such as the house-buyer evaluation task from real-world applications and various benchmark tasks, clearly demonstrate that our new algorithm robustly outperforms many competitive methods.

关键词： weakly-supervised learning time-series classification class-imbalanced learning

A Region-Based Analysis for the Feature Concatenation in Deep Forests

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第6期31卷 1072-1080页

作者： LYU Shen-Huan CHEN Yi-He ZHOU Zhi-Hua national key laboratory for novel software technology Nanjing University

Deep forest is a tree-based deep model made up of non-differentiable modules that are trained without backpropagation. Despite the fact that deep forests have achieved considerable success in a variety of tasks, feature concatenation, as the ingredient for forest representation learning, still lacks theoretical understanding. In this paper, we aim to understand the influence of feature concatenation on predictive performance. To enable such theoretical studies, we present the first mathematical formula of feature concatenation based on the two-stage structure, which regards the splits along new features and raw features as a region selector and a region classifier respectively. Furthermore, we prove a region-based generalization bound for feature concatenation,which reveals the trade-off between Rademacher complexities of the two-stage structure and the fraction of instances that are correctly classified in the selected *** a consequence, we show that compared with the prediction-based feature concatenation(PFC), the advantage of interaction-based feature concatenation(IFC) is that it obtains more abundant regions through distributed representation and alleviates the overfitting risk in local regions. Experiments confirm the correctness of our theoretical results.

关键词： trees (mathematics) raw features pattern classification deep learning (artificial intelligence) deep forest prediction-based feature concatenation forest representation learning tree-based deep model learning (artificial intelligence) region-based generalization feature extraction region-based analysis backpropagation interaction-based feature concatenation

Learnware:small models do big

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 39-50页

作者： Zhi-Hua ZHOU Zhi-Hao TAN national key laboratory for novel software technology Nanjing University

There are complaints about current machine learning techniques such as the requirement of a huge amount of training data and proficient training skills,the difficulty of continual learning,the risk of catastrophic forgetting,and the leaking of data privacy/*** research efforts have been focusing on one of those concerned issues separately,paying less attention to the fact that most issues are entangled in *** prevailing big model paradigm,which has achieved impressive results in natural language processing and computer vision applications,has not yet addressed those issues,whereas becoming a serious source of carbon *** article offers an overview of the learnware paradigm,which attempts to enable users not to need to build machine learning models from scratch,with the hope of reusing small models to do things even beyond their original purposes,where the key ingredient is the specification which enables a trained model to be adequately identified to reuse according to the requirement of future users who know nothing about the model in advance.

关键词： artificial intelligence machine learning learnware

Enhancing unsupervised domain adaptation by exploiting the conceptual consistency of multiple self-supervised tasks

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第4期66卷 126-139页

作者： Hui SUN Ming LI national key laboratory for novel software technology Nanjing University

Unsupervised domain adaptation(UDA) aims to transfer the knowledge from a label-rich source domain to an unlabeled target domain. Current approaches mainly focus on aligning the target domain’s data distribution with the source domain, but lacking attention to allowing target data to guide which features need to be captured. Source data dominates feature extraction. As a result, target embedding would lose some vital discriminative features and limit UDA in complex tasks. In this paper, we argue that utilizing auxiliary tasks to capture target-intrinsic patterns, which do not depend on source supervision, could further enhance UDA. Multiple auxiliary tasks understand the instance concept from different *** findings show that exploiting the conceptual consistency of multiple auxiliary tasks to characterize the common part of these various understandings should reveal the target’s hidden ground truth. Furthermore, we propose a novel method named multiple self-supervision conceptual consistency domain adaptation(MSCC). Experiments and analysis on benchmark datasets show the effectiveness of our idea and method.

关键词： deep learning transfer learning domain adaptation domain shift self-supervised

software Defect Detection with ROCUS

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & technology 2011年第2期26卷 328-342页

作者：姜远黎铭周志华 national key laboratory for novel software technology Nanjing University

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.

关键词： machine learning data mining semi-supervised learning class-imbalance software defect detection

维普期刊数据库

在线全文

学校读者我要写书评

暂无评论

Deep forest

national Science Review 2019年第1期6卷 74-86页

作者： Zhi-Hua Zhou Ji Feng national key laboratory for novel software technology Nanjing University

Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines,we conjecture that the success of deep neural networks owes much to three characteristics, ***-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand,our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation.

关键词： deep forest deep learning machine learning ensemble methods decision trees

Open-environment machine learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

national Science Review 2022年第8期9卷 211-221页

作者： Zhi-Hua Zhou national key laboratory for novel software technology Nanjing University

Conventional machine learning studies generally assume close-environment scenarios where important factors of the learning process hold invariant. With the great success of machine learning, nowadays, more and more practical tasks, particularly those involving open-environment scenarios where important factors are subject to change, called open-environment machine learning in this article, are present to the ***, it is a grand challenge for machine learning turning from close environment to open environment. It becomes even more challenging since, in various big data tasks, data are usually accumulated with time, like streams, while it is hard to train the machine learning model after collecting all data as in conventional studies. This article briefly introduces some advances in this line of research,focusing on techniques concerning emerging new classes, decremental/incremental features, changing data distributions and varied learning objectives, and discusses some theoretical issues.

关键词： machine learning artificial intelligence open-environment machine learning open ML

Variable solution structure can be helpful in evolutionary optimization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2015年第11期58卷 145-161页

作者： QIAN Chao YU Yang ZHOU Zhi-Hua national key laboratory for novel software technology Nanjing University Collaborative Innovation Center of novel software technology and Industrialization

Evolutionary algorithms are a family of powerful heuristic optimization algorithms where various representations have been used for solutions. Previous empirical studies have shown that for achieving a better efficiency of evolutionary optimization, it is often helpful to adopt rich representations(e.g., trees and graphs)rather than ordinary representations(e.g., binary coding). Such a recognition, however, has little theoretical justifications. In this paper, we present a running time analysis on genetic programming. In contrast to previous theoretical efforts focused on simple synthetic problems, we study two classical combinatorial problems, the maximum matching and the minimum spanning tree problems. Our theoretical analysis shows that evolving tree-structured solutions is much more efficient than evolving binary vector encoded solutions, which is also verified by experiments. The analysis discloses that variable solution structure might be helpful in evolutionary optimization when the solution complexity can be well controlled.

关键词： evolutionary algorithms genetic programming maximum matching minimum spanning tree running time computational complexity

Abductive learning: towards bridging machine learning and logical reasoning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第7期62卷 220-222页

作者： Zhi-Hua ZHOU national key laboratory for novel software technology Nanjing University

In the history of artificial intelligence research,machine learning and logical reasoning have almost been separately developed. It is often argued that advanced intelligent technologies would emerge when machine lear... 详细信息

关键词： pro towards bridging machine learning and logical reasoning Abductive learning