检索结果-内蒙古大学图书馆

Open-world knowledge graph completion for unseen entities and relations via attentive feature aggregation

INFORMATION SCIENCES 2022年 586卷 468-484页

作者： Oh, Byungkook Seo, Seungmin Hwang, Jimin Lee, Dongho Lee, Kyong-Ho Yonsei Univ Dept Comp Sci Seoul South Korea

Most of knowledge graph completion (KGC) models are designed for static KGs where entity and relation sets are fixed. These approaches are inherently transductive because they simply predict the plausibility of facts whose entities and relations had to previously appear in the training phase. However, since entities and relations are constantly added, removed, or changed over time, KGC models should be able to generalize to out-of-KG entities and relations in evolving KGs, which are more suited to real-world scenarios. Moreover, incorporating global graph-structured information into KGC models is another challenging issue. To overcome these issues, this paper proposes a novel Inductive KG Embedding (IKGE) model for open-world KGC, which accommodates out-of-KG entities and relations. Unlike training individual unique embeddings, the proposed model fundamentally learns an embedding generator function to elaborately generate fact embeddings in an inductive manner. Specifically, the feature information of each fact is extracted as a vector from its entity-related and relation-related side information via an attention mechanism. Then, to score a given fact, our neighborhood feature aggregator hierarchically accumulates the feature information of multi-hop neighbors. Experimental results show that IKGE outperforms existing approaches in both transductive and inductive setups by successfully aggregating neighborhood features.(c) 2021 Elsevier Inc. All rights reserved.

关键词： Knowledge graph embedding Link prediction graph-based learning graph convolutional networks Deep learning Attention model

来源：评论

学校读者我要写书评

暂无评论

On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms

The Journal of Machine Learning Research

引用

The Journal of Machine learning Research 2020年第1期21卷 1022-1068页

作者： Nicolás García Trillos Zachary Kaplan Thabo Samakhoana Daniel Sanz-Alonso Department of Statistics University of Wisconsin-Madison Madison WI Division of Applied Mathematics Brown University Providence RI Department of Statistics University of Chicago Chicago IL

This paper considers a Bayesian approach to graph-based semi-supervised learning. We show that if the graph parameters are suitably scaled, the graph-posteriors converge to a continuum limit as the size of the unlabeled data set grows. This consistency result has profound algorithmic implications: we prove that when consistency holds, carefully designed Markov chain Monte Carlo algorithms have a uniform spectral gap, independent of the number of unlabeled inputs. Numerical experiments illustrate and complement the theory.

关键词： semi-supervised learning graph-based learning Markov chain Monte Carlo spectral gap

来源：评论

学校读者我要写书评

暂无评论

Deep Semi-supervised Label Propagation for SAR Image Classification 30

Deep Semi-supervised Label Propagation for SAR Image Classif...

引用

Conference on Algorithms for Synthetic Aperture Radar Imagery XXX

作者： Enwright, Joshua Hardiman-Mostow, Harris Calder, Jeff Bertozzi, Andrea Univ Calif Los Angeles Dept Math 520 Portola Plaza Los Angeles CA 90095 USA Univ Minnesota Sch Math 538 Vincent Hall206 Church St SE Minneapolis MN 55455 USA

ISBN: (纸本)9781510661547;9781510661554

Automatic target recognition with synthetic aperture radar (SAR) data is a challenging problem due to the complexity of the images and the difficulty in acquiring labels. Recent work(1) used a convolutional variational autoencoder to extract relevant features prior to constructing a similarity graph in a graph-based active learning framework for SAR data. In this work we present two novel methods for classifying SAR data that use convolutional neural network (CNN) feature extraction together with techniques from graph-based semi-supervised learning in an end-to-end manner that can provide improved classification performance in the small labeled dataset regimes that are common in SAR ATR. First, we introduce Laplace Output Activation Neural Networks (LOAN Networks) as a way of directly optimizing feature embeddings for use with graph-based semi-supervised learning techniques. Next, we introduce Pseudo Label Propagation Neural Networks (PsLaPN Networks) as a inexpensive way to both boost the training signal as well as combat overconfidence and poor model calibration in neural networks. We present a novel derivation of simple formulas for the direct and efficient computation of derivatives of the outputs of graph-based algorithms like label propagation2 for use in the training of our networks. We test the proposed end-to-end networks for active learning on OpenSARShip, a SAR dataset, where both methods surpass the previous state-of-the-art.

关键词： graph-based learning Deep learning Pseudolabeling Synthetic Aperture Radar

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised multi-label classification using an extended graph-based manifold regularization

引用

COMPLEX & INTELLIGENT SYSTEMS 2022年第2期8卷 1561-1577页

作者： Li, Ding Dick, Scott Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 1H9 Canada

graph-based algorithms are known to be effective approaches to semi-supervised learning. However, there has been relatively little work on extending these algorithms to the multi-label classification case. We derive an extension of the Manifold Regularization algorithm to multi-label classification, which is significantly simpler than the general Vector Manifold Regularization approach. We then augment our algorithm with a weighting strategy to allow differential influence on a model between instances having ground-truth vs. induced labels. Experiments on four benchmark multi-label data sets show that the resulting algorithm performs better overall compared to the existing semi-supervised multi-label classification algorithms at various levels of label sparsity. Comparisons with state-of-the-art supervised multi-label approaches (which of course are fully labeled) also show that our algorithm outperforms all of them even with a substantial number of unlabeled examples.

关键词： Manifold regularization Multi-label classification Semi-supervised learning graph-based learning

来源：评论

学校读者我要写书评

暂无评论

Significance of Emphasized Features for Good Representation on Deep Metric learning 19

Significance of Emphasized Features for Good Representation ...

引用

IEEE/ACIS 19th International Conference on Software Engineering Research, Management and Applications (SERA)

作者： Saeki, Shozo Kawahara, Minoru Aman, Hirohisa Ehime Univ Grad Sch Sci & Engn Matsuyama Ehime 7908577 Japan FINDEX Inc Business Strategy Dept 4-9-6 Sanbancho Matsuyama Ehime 7900003 Japan Ehime Univ Ctr Informat Technol Matsuyama Ehime 7908577 Japan

ISBN: (纸本)9781728176772

Deep metric learning (DML) learns the mapping, which maps into embedding space in which similar data is near and dissimilar data is far. Most DML frameworks apply L2 normalization to feature vectors, and these feature vectors are non-sparse [6], [10], [30]. In this paper, we propose to apply L1 regularization loss to feature vectors. Proposed regularization emphasizes important features and restraints unimportant features on L2 normalized features. L1 regularization can combine with general DML losses because L1 regularization only regularizes feature vectors. In this paper, we finally propose SparseSoft-Triple loss, which is a combination of SoftTriple loss and L1 regularization. We demonstrate the effectiveness of the proposed SparseSoftTriple loss on some data sets for image retrieval tasks and fine-grained images.

关键词： semi-supervised learning graph-based learning manifold regularization classification optimization

来源：评论

学校读者我要写书评

暂无评论

Capped l1-norm regularized least squares classification with label noise

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021年第3期40卷 4051-4063页

作者： Yang, Zhi Gan, Haitao Li, Xuan Wu, Cong Hubei Univ Technol Sch Comp Sci Wuhan Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou Peoples R China Wuhan Inst Technol Sch Elect & Informat Engn Wuhan Hubei Peoples R China

Since label noise can hurt the performance of supervised learning (SL), how to train a good classifier to deal with label noise is an emerging and meaningful topic in machine learning field. Although many related methods have been proposed and achieved promising performance, they have the following drawbacks: (1) They can lead to data waste and even performance degradation if the mislabeled instances are removed;and (2) the negative effect of the extremely mislabeled instances cannot be completely eliminated. To address these problems, we propose a novel method based on the capped l(1) norm and a graph-based regularizer to deal with label noise. In the proposed algorithm, we utilize the capped l(1) norm instead of the l(1) norm. The used norm can inherit the advantage of the l(1) norm, which is robust to label noise to some extent. Moreover, the capped l(1) norm can adaptively find extremely mislabeled instances and eliminate the corresponding negative influence. Additionally, the proposed algorithm makes full use of the mislabeled instances under the graph-based framework. It can avoid wasting collected instance information. The solution of our algorithm can be achieved through an iterative optimization approach. We report the experimental results on several UCI datasets that include both binary and multi-class problems. The results verified the effectiveness of the proposed algorithm in comparison to existing state-of-the-art classification methods.

关键词： Artificial intelligence classification algorithm graph-based learning label noise l(1) norm

来源：评论

学校读者我要写书评

暂无评论

Progressive graph Convolutional Networks for Semi-Supervised Node Classification

引用

IEEE ACCESS 2021年 9卷 81957-81968页

作者： Heidari, Negar Iosifidis, Alexandros Aarhus Univ Dept Elect & Comp Engn DK-8000 Aarhus Denmark

graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification. Existing methods use a network structure defined by the user based on experimentation with fixed number of layers and neurons per layer and employ a layer-wise propagation rule to obtain the node embeddings. Designing an automatic process to define a problem-dependant architecture for graph convolutional networks can greatly help to reduce the need for manual design of the structure of the model in the training process. In this paper, we propose a method to automatically build compact and task-specific graph convolutional networks. Experimental results on widely used publicly available datasets show that the proposed method outperforms related methods based on convolutional graph networks in terms of classification performance and network compactness.

关键词： Network topology Topology Convolution Neurons Training Task analysis Optimization graph-based learning graph convolutional networks progressive learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

graph Adversarial Training: Dynamically Regularizing based on graph Structure

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2021年第6期33卷 2493-2504页

作者： Feng, Fuli He, Xiangnan Tang, Jie Chua, Tat-Seng Natl Univ Singapore Comp 1 Sch Comp Comp Dr Singapore 117417 Singapore Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China Tsinghua Univ Beijing 100084 Peoples R China

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citation link tend to be in the same class), graph neural networks could be more sensitive to the perturbations, since the perturbations from connected examples exacerbate the impact on a target example. Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization. However, existing AT methods focus on standard classification, being less effective when training models on graph since it does not model the impact from connected examples. In this work, we explore adversarial training on graph, aiming to improve the robustness and generalization of models learned on graph. We propose graph Adversarial Training (graphAT), which takes the impact from connected examples into account when learning to construct and resist perturbations. We give a general formulation of graphAT, which can be seen as a dynamic regularization scheme based on the graph structure. To demonstrate the utility of graphAT, we employ it on a state-of-the-art graph neural network model - graph Convolutional Network (GCN). We conduct experiments on two citation graphs (Citeseer and Cora) and a knowledge graph (NELL), verifying the effectiveness of graphAT which outperforms normal training on GCN by 4.51 percent in node classification accuracy. Codes are available via: https://***/fulifeng/graphAT.

关键词： Perturbation methods Training Neural networks Robustness Predictive models Task analysis Standards Adversarial training graph-based learning graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiview Semi-Supervised learning Model for Image Classification

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2020年第12期32卷 2389-2400页

作者： Nie, Feiping Tian, Lai Wang, Rong Li, Xuelong Northwestern Polytech Univ Sch Comp Sci Xian 710072 Shaanxi Peoples R China Northwestern Polytech Univ Ctr OPT IMagery Anal & Learning OPTIMAL Xian 710072 Shaanxi Peoples R China

Semi-supervised learning models for multiview data are important in image classification tasks, since heterogeneous features are easy to obtain and semi-supervised schemes are economical and effective. To model the view importance, conventional graph-based multiview learning models learn a linear combination of views while assuming a priori weights distribution. In this paper, we present a novel structural regularized semi-supervised model for multiview data, termed Adaptive MUltiview SEmi-supervised model (AMUSE). Our new model learns weights from a priori graph structure, which is more reasonable than weight regularization. Theoretical analysis reveals the significant difference between AMUSE and the prior arts. An efficient optimization algorithm is provided to solve the new model. Experimental results on six real-world data sets demonstrate the effectiveness of the structural regularized weights learning scheme.

关键词： Multiview learning graph-based learning semi-supervised learning image classification structured graph

来源：评论

学校读者我要写书评

暂无评论

Stock ranking prediction using a graph aggregation network based on stock price and stock relationship information

引用

INFORMATION SCIENCES 2023年第1期643卷

作者： Song, Guowei Zhao, Tianlong Wang, Suwei Wang, Hua Li, Xuemei Shandong Univ Sch Software Jinan 250101 Peoples R China Ludong Univ Sch Informat & Elect Engn Yantai 264025 Peoples R China

The volatility of stock prices makes it difficult to predict stock price trends correctly. This volatility is affected by many factors, including other stocks related to it. Stock prediction based on graph learning uses various graph neural networks to learn how stocks interact to provide more information. However, they tend to adopt statically defined stock relations based on prior knowledge (such as industry relations and Wiki relations), making it difficult to capture the interplay between stocks over time. In addition, their predictions mostly rely on a single stock relationship, while many types of stock relationships affect the volatility of stock prices in a complex and intertwined manner. A new price similarity relation graph is first constructed using the multi-view stock price similarity to capture dynamic stock relationships. based on three stock graphs (price similarity, Wiki and industry), we further propose a multi-relational graph attention ranking (MGAR) network. In MGAR, the multi-graph aggregation is achieved by applying adaptive learning mechanisms, thereby forming effective relation embeddings. When combined with the captured price trend embedding, MGAR model gives a ranking list of future returns and chooses K stocks with the best returns to trade so that the return on investment is maximized. Extensive experiments demonstrate that MGAR method outperforms state-of-the-art stock predicting solutions, achieving average returns of 164% and 236% on two real datasets, respectively.

关键词： Stock return ranking graph-based learning Stock price relation graph convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：