检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Chunxu Zhang, Zijian Long, Guodong Yan, Peng Zhou, Tianyi Yang, Bo College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China College of Computer Science and Technology Jilin University City University of Hong Kong China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Sydney Australia Computer Science and UMIACS University of Maryland Maryland United States

Federated recommendation systems usually trains a global model on the server without direct access to users’ private data on their own devices. However, this separation of the recommendation model and users’ private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings. This paper introduces a novel method called Item-aligned Federated Aggregation (IFedRec) to address this challenge. It is the first research work in federated recommendation to specifically study the cold-start scenario. The proposed method learns two sets of item representations by leveraging item attributes and interaction records simultaneously. Additionally, an item representation alignment mechanism is designed to align two item representations and learn the meta attribute network at the server within a federated learning framework. Experiments on four benchmark datasets demonstrate IFedRec’s superior performance for cold-start scenarios. Furthermore, we also verify IFedRec owns good robustness when the system faces limited client participation and noise injection, which brings promising practical application potential in privacy-protection enhanced federated recommendation systems. The implementation code is available1 Copyright © 2023, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Fast Explainable Recommendation Model by Combining Fine-Grained Sentiment in Review Data

引用

computational Intelligence and Neuroscience 2022年第0期2022卷 4940401页

作者： Wang, Ying He, Xin Wang, Hongji Sun, Yudong Wang, Xin College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China College of Artificial Intelligence Jilin University Changchun130012 China

With the rapid development of e-commerce, recommendation system has become one of the main tools that assists users in decision-making, enhances user's experience, and creates economic value. Since it is difficult to explain the implicit features generated by matrix factorization, explainable recommendation system has attracted more and more attention recently. In this paper, we propose an explainable fast recommendation model by combining fine-grained sentiment in review data (FSER, (Fast) Fine-grained Sentiment for Explainable Recommendation). We innovatively construct user-rating matrix, user-aspect sentiment matrix, and item aspect-descriptive word frequency matrix from the review-based data. And the three matrices are reconstructed by matrix factorization method. The reconstructed results of user-aspect sentiment matrix and item aspect-descriptive word frequency matrix can provide explanation for the final recommendation results. Experiments in the Yelp and Public Comment datasets demonstrate that, compared with several classical models, the proposed FSER model is in the optimal recommendation accuracy range and has lower sparseness and higher training efficiency than tensor models or neural network models;furthermore, it can generate explanatory texts and diagrams that have high interpretation quality. © 2022 Ying Wang et al.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Zero-shot user intent detection via capsule neural networks

arXiv

引用

arXiv 2018年

作者： Xia, Congying Zhang, Chenwei Yan, Xiaohui Chang, Yi Yu, Philip S. Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States Huawei Technologies San JoseCA95050 United States College of Artificial Intelligence Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China

User intent detection plays a critical role in question-answering and dialog systems. Most previous works treat intent detection as a classification problem where utterances are labeled with predefined intents. However, it is labor-intensive and time-consuming to label users' utterances as intents are diversely expressed and novel intents will continually be involved. Instead, we study the zero-shot intent detection problem, which aims to detect emerging user intents where no labeled utterances are currently available. We propose two capsule-based architectures: IntentCapsNet that extracts semantic features from utterances and aggregates them to discriminate existing intents, and IntentCapsNet-ZSL which gives IntentCapsNet the zero-shot learning ability to discriminate emerging intents via knowledge transfer from existing intents. Experiments on two real-world datasets show that our model not only can better discriminate diversely expressed existing intents, but is also able to discriminate emerging intents when no labeled utterances are available. Copyright © 2018, The Authors. All rights reserved.

关键词： knowledge management

来源：评论

学校读者我要写书评

暂无评论

PepLand: A large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids

arXiv

引用

arXiv 2023年

作者： Zhang, Ruochi Wu, Haoran Xiu, Yuting Li, Kewei Chen, Ningning Wang, Yu Wang, Yan Gao, Xin Zhou, Fengfeng Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Jilin Changchun130012 China School of Artificial Intelligence Jilin University Changchun130012 China Syneron Technology Guangzhou510700 China College of Computer Science and Technology Jilin University Jilin Changchun130012 China Thuwal23955 Saudi Arabia Thuwal23955 Saudi Arabia

In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation. These peptides present promising modifications to biological, pharmacological, and physiochemical attributes in both endogenous and engineered peptides. Notwithstanding their considerable advantages, the scientific community exhibits a conspicuous absence of an effective pre-trained model adept at distilling feature representations from such complex peptide sequences. We herein propose PepLand, a novel pre-training architecture for representation and property analysis of peptides spanning both canonical and non-canonical amino acids. In essence, PepLand leverages a comprehensive multi-view heterogeneous graph neural network tailored to unveil the subtle structural representations of peptides. Empirical validations underscore PepLand's effectiveness across an array of peptide property predictions, encompassing protein-protein interactions, permeability, solubility, and synthesizability. The rigorous evaluation confirms PepLand's unparalleled capability in capturing salient synthetic peptide features, thereby laying a robust foundation for transformative advances in peptide-centric research domains. We have made all the source code utilized in this study publicly accessible via GitHub at https://***/zhangruochi/pepland. © 2023, CC BY-NC-ND.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

SSBM: A Signed Stochastic Block Model for Multiple Structure Discovery in Large-Scale Exploratory Signed Networks

arXiv

引用

arXiv 2023年

作者： Li, Yang Yang, Bo Zhao, Xuehua Yang, Zhejian Chen, Hechang Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China Aviation University of Air Force Changchun130062 China School of Digital Media Shenzhen Institute of Information Technology Shenzhen518055 China School of Artificial Intelligence Jilin University Changchun130012 China

Signed network structure discovery has received extensive attention and has become a research focus in the field of network science. However, most of the existing studies are focused on the networks with a single structure, e.g., community or bipartite, while ignoring multiple structures, e.g., the coexistence of community and bipartite structures. Furthermore, existing studies were faced with challenge regarding large-scale signed networks due to their high time complexity, especially when determining the number of clusters in the observed network without any prior knowledge. In view of this, we propose a mathematically principled method for signed network multiple structure discovery named the Signed Stochastic Block Model (SSBM). The SSBM can capture the multiple structures contained in signed networks, e.g., community, bipartite, and coexistence of them, by adopting a probabilistic model. Moreover, by integrating the minimum message length (MML) criterion and component-wise EM (CEM) algorithm, a scalable learning algorithm that has the ability of model selection is proposed to handle large-scale signed networks. By comparing state-of-the-art methods on synthetic and realworld signed networks, extensive experimental results demonstrate the effectiveness and efficiency of SSBM in discovering large-scale exploratory signed networks with multiple structures. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Fold-based meta-analysis: a method for identifying differentially expressed genes in microarray data

引用

Journal of Information and computational Science 2013年第11期10卷 3453-3462页

作者： Tian, Yuan Bai, Tian Liu, Guixia Li, Zhangxiu Wu, Jianan Zhou, Chunguang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China College of Computer Science and Technology Changchun University Changchun 130022 China

The increase of microarray experiments brings a fresh challenge to analyze microarray data across datasets. Several methods have been developed and implemented. But the current tools were either complicated software with inefficiency methods or web applications, among which some were limited to specific data format. In this paper, we propose Fold-based Meta-analysis (FM), a method to identify Differentially Expressed Genes (DEGs) in microarray data. It could meta-analyze datasets in either the same or different platforms. We test FMT, respectively, on two published Arabidopsis datasets in one platform and three Mouse datasets in three different platforms, and then analyze the Gene Ontology (GO) terms or metabolic pathways of the most DEGs. Our results show that they are highly agreed on DEGs, and many of them are crucial and functional. In summary, our method is fast and practical. © 2013 Binary Information Press.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Aggregation tree constructing algorithm based on energy consumption assessment

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2008年第1期45卷 104-109页

作者： Sun, Dayang Liu, Yanheng Wang, Aimin College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun 130012 China College of Computer Science and Technology Harbin Engineering University Harbin 150001 China

This paper first gives an analysis of data aggregation and data compression based on energy consumption of sensor nodes, after which an approach is proposed to construct an aggregation tree in the case of non-perfect aggregation, since GIT considers only the case of perfect aggregation and it does not work well if the aggregation is non-perfect. An assessment scheme that can get the information of hops from the aggregation point to the sink and the hops from the aggregation point to the source node is used to construct such an aggregation tree. Moreover, the energy consumption of the aggregation is also considered. This scheme can be used when perfect aggregation cannot be performed. In this paper, an approach to reduce the cost of reinforcement is also proposed, in which the reinforcement work is done by the source nodes themselves, not by the sink node. Simulation result shows that this approach can save more energy than GIT when the aggregation ratio is small. This result also provides a theoretical limit of aggregation to tell when GIT will lose its superiority and thus gives a direction to choose among the aggregation algorithms. Another result shows that the further the sources are away from the sink, the less reinforcement messages are needed. Finally a guidance to tell when to use the EGA (energy consumption assessment) scheme is given.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A hybrid algorithm of minimum spanning tree and nearest neighbor for classifying human cancers

A hybrid algorithm of minimum spanning tree and nearest neig...

引用

International Conference on Advanced Computer Theory and engineering, ICACTE

作者： Chunbao Zhou Liming Wan Yanchun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China Research Institute on General Development and Evaluation of Equipment EAAF of PLA Beijing China

ISBN: (纸本)9781424465392

Classification and prediction of different cancers based on gene expression profiles are important for cancer diagnosis, cancer treatment and medication discovery. The k nearest neighbor algorithm (k-NN) is one easy and efficient machine learning method for cancer classification and the parameter k is crucial. In this paper, we integrate minimum spanning tree (MST) and k nearest neighbor algorithm (k-NN) for cancer classification. The MST is designed for the selection of parameter k and the nearest neighbors for k-NN. Firstly we build a minimum spanning tree (MST) based on Euclidean distance between each two samples for gene expression data only including one unknown class sample. Secondly for unknown class sample in the gene expression data, we find the connected samples and then apply majority vote principle. Thirdly if there are tied votes then we expend the connected samples with the nearest neighbors for unknown class sample until all the samples are expended or the class for unknown sample is obtained. This hybrid algorithm is referred to as MSTNN. The hybrid algorithm MSTNN is compared with k-NN and other 3 existing classification algorithms on CNS dataset, Colon dataset and Lung dataset, 3 binary class gene expression datasets and 3 multi-class gene expression datasets: Leukemia1, Leukemia2, and Leukemia3 involving human cancers. The MSTNN algorithm improves 5.65% better than k-NN on average LOOCV accuracy and 13.80% better than k-NN on testing datasets classification average accuracy, and achieves the best performance in all the 5 algorithms. The results demonstrate that the proposed MSTNN algorithm is feasible to classify human cancers.

关键词： Classification algorithms Artificial neural networks Niobium Lungs Colon Support vector machines Cancer

来源：评论

学校读者我要写书评

暂无评论

Prewavelets with finite decomposition and finite reconstruction

引用

Journal of Information and computational Science 2007年第1期4卷 35-41页

作者： Guan, Yujing Li, Ying Jiang, Zhengyi Institute of Mathematics Jilin University Changchun 130021 China State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing 100084 China College of Computer Science and Technology Jilin University Changchun 130021 China Key Laboratory of Symbol Computation and Knowledge Engineering Changchun 130021 China

The necessary and sufficient condition for the existence of prewavelets with finite decomposition and finite reconstruction is presented. Especially when r = 1, we show that {φj(x-k) | 1 &le j &le r, k ∈ s} is shift-orthogonal if there exist prewavelets with finite decomposition and finite reconstruction, i.e., non-trivial prewavelets with finite decomposition and finite reconstruction does not exist. As an example, when r = 2 we construct a prewavelet with finite decomposition and finite reconstruction where the scale function is not shift-orthogonal, which demonstrate that there exist vector prewavelets with finite decomposition and finite reconstruction.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Novel Drug-Drug Interaction Prediction Model Based on Line Subgraph Generation Strategy

A Novel Drug-Drug Interaction Prediction Model Based on Line...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian Bai Chu Li Xinyue Peng Haotian Guan Zefan Zhang Guishen Wang College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China College of Software Jilin University Changchun China School of Nursing Jilin University Changchun China School of Life Sciences Jilin University Changchun China College of Computer Science and Engineering Changchun University of Technology Changchun China

Drug-Drug Interaction (DDI) prediction task is helpful for better-understanding drugs. In this paper, we propose a novel drug-drug interaction prediction model based on line subgraph generation strategy, named DDI-LSG model. Our DDI-LSG model consists of three main parts which include drug relation graph construction, line subgraph generation strategy, and graph-level classification. To consider more relationships among drugs, we propose a node feature-enhancing method to encode drug features in drug relation graph construction process. To consider drugs and DDI as equivalent factors of our DDI-LSG model, we introduce line graph transformation to integrate DDI with drug feature enhancing vector. Combining Jaccard similarity with cosine similarity, we propose a line subgraph generation strategy to evaluate node relation and extract key structures around target DDI in the line graph. Then, we reformulate the DDI prediction task into a graph-level classification task for the line subgraph of the target DDI. Therefore, in the final part of our DDI-LSG model, we use a graph-level classifier to classify the line subgraphs. Our DDI-LSG model outperforms better experiment results than baselines. Ablation results have validated the node feature enhancing method and line subgraph generation strategy.

关键词：

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：