检索结果-内蒙古大学图书馆

2nd International Symposium on Benchmarking, Measuring, and Optimization, Bench 2019

作者： Li, Guangli Wang, Xueying Ma, Xiu Liu, Lei Feng, Xiaobing State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China College of Computer Science and Technology Jilin University Changchun China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun China

ISBN: (纸本)9783030495558

In this paper, we present XDN, an optimization and inference engine for accelerating residual neural networks on Cambricon chips. We leverage a channel pruning method to compress the weights of ResNet-50. By exploring the optimization opportunities in computational graphs, we propose a layer fusion strategy, which dramatically decreases the number of scalar computation layers, such as Batch Normalization, Scale. Furthermore, we design an efficient implementation of XDN, including data preprocessing, hyper-parameter auto-tuning, etc. The experimental results show that the ResNet-50 model can achieve significant speedup without accuracy loss by using our XDN engine. © Springer Nature Switzerland AG 2020.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

ESAE: Evolutionary Strategy-Based Architecture Evolution 14th

ESAE: Evolutionary Strategy-Based Architecture Evolution

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Gu, Xue Meng, Ziyao Liang, Yanchun Xu, Dong Huang, Han Han, Xiaosong Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Zhuhai College of Jilin University Zhuhai519041 China Department of Electrical Engineering and Computer Science Informatics Institute and Christopher S. Bond Life Sciences Center University of Missouri ColumbiaMO65211 United States School of Software Engineering South China University of Technology GuangZhou510006 China

ISBN: (纸本)9789811534249

Although deep neural networks (DNNs) play important roles in many fields, the architecture design of DNNs can be challenging due to the difficulty of input data representation, the huge number of parameters and the complex layer relationships. To overcome the obstacles of architecture design, we developed a new method to generate the optimal structure of DNNs, named Evolutionary Strategy-based Architecture Evolution (ESAE), consisting of a bi-level representation and a probability distribution learning approach. The bi-level representation encodes architectures in the gene and parameter levels. The probability distribution learning approach ensures the efficient convergence of the architecture searching process. By using Fashion-MNIST and CIFAR-10, the effectiveness of the proposed ESAS is verified. The evolved DNNs, starting from a trivial initial architecture with one single convolutional layer, achieved the accuracies of 94.48% and 93.49% on Fashion-MNIST and CIFAR-10, respectively, and require remarkably less hardware costs in terms of GPUs and running time, compared with the existing state-of-the-art manual screwed architectures. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Attentive Implicit Relation Embedding for Social Recommendation

SSRN

引用

SSRN 2022年

作者： Ma, Xintao Dong, Liyan Wang, Yuequn Li, Yongli Liu, Zhen Zhang, Hao College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Information Science and Technology Northeast Normal University Changchun130117 China Graduate School of Engineering Nagasaki Institute of Applied Science 536 Aba-machi Nagasaki851-0193 Japan

Nowadays, recommendation system incorporating social networks has attracted a lot of research attention and is widely used to understand user preferences regarding social relations. Besides, graph neural networks(GNNs) have proven to learn graph-structured data effectively. Thus, integrating GNN into social recommendations has become one challenge. Many approaches encode both the user-item interaction and social relations to learn user preference. However, the implicit relations are also crucial to understanding the features of users and items. Thus, we propose the attentive implicit relation embedding for social recommendation(SR-AIR), which models the user-item interaction and social networks, utilizing a graph attention mechanism on implicit relations of users and items. We evaluate our framework on two real-world datasets and demonstrate that our framework performs the best compared with state-of-the-art baselines © 2022, 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

PepHarmony: A Multi-View Contrastive Learning Framework for Integrated Sequence and Structure-Based Peptide Encoding

arXiv

引用

arXiv 2024年

作者： Zhang, Ruochi Wu, Haoran Liu, Chang Li, Huaping Wu, Yuqian Li, Kewei Wang, Yifan Deng, Yifan Chen, Jiahui Zhou, Fengfeng Gao, Xin Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Jilin Changchun130012 China School of Artificial Intelligence Jilin University Jilin Changchun130012 China Syneron Technology Guangzhou510700 China Beijing Life Science Academy Beijing102209 China School of Biomedical Sciences LKS Faculty of Medicine The University of Hong Kong Hong Kong Thuwal23955 Saudi Arabia Thuwal23955 Saudi Arabia College of Software Jilin University Jilin Changchun130012 China College of Computer Science and Technology Jilin University Jilin Changchun130012 China

Recent advances in protein language models have catalyzed significant progress in peptide sequence representation. Despite extensive exploration in this field, pre-trained models tailored for peptide-specific needs remain largely unaddressed due to the difficulty in capturing the complex and sometimes unstable structures of peptides. This study introduces a novel multi-view contrastive learning framework PepHarmony for the sequence-based peptide encoding task. PepHarmony innovatively combines both sequence- and structure-level information into a sequence-level encoding module through contrastive learning. We carefully select datasets from the Protein Data Bank (PDB) and AlphaFold database to encompass a broad spectrum of peptide sequences and structures. The experimental data highlights PepHarmony's exceptional capability in capturing the intricate relationship between peptide sequences and structures compared with the baseline and fine-tuned models. The robustness of our model is confirmed through extensive ablation studies, which emphasize the crucial roles of contrastive loss and strategic data sorting in enhancing predictive performance. The proposed PepHarmony framework serves as a notable contribution to peptide representations, and offers valuable insights for future applications in peptide drug discovery and peptide engineering. We have made all the source code utilized in this study publicly accessible via GitHub at https://***/zhangruochi/PepHarmony or http://***/supp/. © 2024, 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

Curvature regularization to prevent distortion in graph embedding 34

Curvature regularization to prevent distortion in graph embe...

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Pei, Hongbin Wei, Bingzhe Chang, Kevin Chen-Chuan Zhang, Chunxu Yang, Bo College of Computer Science and Technology Jilin University China Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign United States Department of Computer Science University of Illinois Urbana-Champaign United States Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education China

Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding Euclidean space, and hence to detect them becomes difficult for machine learning models. To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. We present a novel angle-based sectional curvature, termed ABS curvature, and accordingly three kinds of curvature regularization to induce flat embedding manifolds during graph embedding. We integrate curvature regularization into five popular proximity-preserving embedding methods, and empirical results in two applications show significant improvements on a wide range of open graph datasets. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A two-stage HV-driven adaptive multi-objective evolutionary algorithm and its application in fixed polarity reed-muller circuits

引用

Expert Systems with Applications 2025年 288卷

作者： Lu Yang Shengsheng Wang Ruyi Dong Zihao Fu College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China College of Information and Control Engineering Jilin Institute of Chemical Technology Changchun 130012 China

To achieve a balance between convergence and diversity, we proposed a two-stage HV-driven adaptive multi-objective evolutionary algorithm (TSAMEA). TSAMEA employs a sinusoidal decreasing parameter adjustment method to enhance exploration pace in the first stage. An adaptive parameter control mechanism utilizes historical memory pools and an HV-driven degree adjustment strategy to achieve better exploitation in the second stage. Extensive experimental data demonstrate that TSAMEA outperforms nine other compared MOEAs. The component analysis illustrates the efficacy of each component of TSAMEA. In addition, area and power optimization are now the main limitations in chip design, TSAMEA is applied to area and power optimization for Fixed Polarity Reed-Muller (FPRM) logic circuits and perform well, which further verifies the ability of the TSAMEA to solve practical problems.

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction 28

ToHRE: A Top-Down Classification Strategy with Hierarchical ...

引用

28th International Conference on computational Linguistics, COLING 2020

作者： Yu, Erxin Han, Wenjuan Tian, Yuan Chang, Yi School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China College of Biological and Agricultural Engineering Jilin University China Department of Computer Science National University of Singapore Singapore

ISBN: (纸本)9781952148279

Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem. Most of the existing approaches address these two problems through flat classification, which lacks hierarchical information of relations. To leverage the informative relation hierarchies, we formulate DSRE as a hierarchical classification task and propose a novel hierarchical classification framework, which extracts the relation in a top-down manner. Specifically, in our proposed framework, 1) we use a hierarchically-refined representation method to achieve hierarchy-specific representation;2) a top-down classification strategy is introduced instead of training a set of local classifiers. The experiments on NYT dataset demonstrate that our approach significantly outperforms other state-of-the-art approaches, especially for the long-tail problem. © 2020 COLING 2020 - 28th International Conference on computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Grid Partition and Agglomeration for Bidirectional Hierarchical Clustering 2nd

Grid Partition and Agglomeration for Bidirectional Hierarchi...

引用

2nd EAI International Conference on Security and Privacy in New Computing Environments, SPNCE 2019

作者： Wu, Lei Chen, Hechang Yu, Xiangchun Chao, Sun Yu, Zhezhou Dou, RuiTing College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China

ISBN: (纸本)9783030213725

Clustering is an important data processing tool, which can be used to reveal the distribution structure of unfamiliar domain data, or as preprocess methods to magnify data object to accelerate subsequent processing or simplify models. However, the distribution of many real-world data in feature space is very complex or uneven. Besides, the similarity/distance is not easy to be properly defined in feature space with different dimensional quantity. Therefore, many existing clustering algorithms are not stable in real datasets, and better performance of different datasets relies on artificial special design, such as scale normalization. In this paper, we propose a bidirectional hierarchical clustering (BHC) algorithm with two phases. In the first phase (Top-down), based on the probability density function of data in different dimensions, the feature space is divided into over-segmented grids to adapt to the complex distribution of data. In the second phase (Bottom-up), based on statistical information, a robust distance instead of geometrical distance is defined to agglomerate the grids into a dendrogram. Compared with the individual data points, grids created in the first phase can carry more statistical information, and the magnified processing objects can accelerate the clustering process. The second phase enhances the algorithm’s ability by the ability of recognize arbitrary shape data clusters. The effectiveness of BHC is compared with 20 popular or recent clustering algorithms on 8 artificial datasets and 6 real-world datasets. And the results show that our algorithm can achieve good results on most datasets. In particular, BHC surpasses all the comparison algorithms involved in the experiment on all real-world datasets. In addition, in order to test the efficiency of the algorithm, we design an experiment which can test the influence of dimension and data size on the operation time. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommuni

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Generative Classifier for Domain Generalization

arXiv

引用

arXiv 2025年

作者： Long, Shaocong Zhou, Qianyu Li, Xiangtai Ying, Chenhao Tong, Yunhai Ma, Lizhuang Luo, Yuan Tao, Dacheng Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Nanyang Technological University Singapore Peking University Beijing China

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods predominantly focus on learning domain invariance across domains, however, such methods overlook the untapped potential inherent in domain-specific information. While the prevailing practice of discriminative linear classifier has been tailored to domain-invariant features, it struggles when confronted with diverse domain-specific information, e.g., intra-class shifts, that exhibits multi-modality. To address these issues, we explore the theoretical implications of relying on domain-invariant features, revealing the crucial role of domain-specific information in mitigating the target risk for DG. Drawing from these insights, we propose Generative Classifier-driven Domain Generalization (GCDG), introducing a generative paradigm for the DG classifier based on Gaussian Mixture Models (GMMs) for each class across domains. GCDG consists of three key modules: Heterogeneity Learning Classifier (HLC), Spurious Correlation Blocking (SCB), and Diverse Component Balancing (DCB). Concretely, HLC attempts to model the feature distributions and thereby capture valuable domain-specific information via GMMs. SCB identifies the neural units containing spurious correlations and perturbs them, mitigating the risk of HLC learning irrelevant spurious patterns. Meanwhile, DCB ensures a balanced contribution of components within HLC, preventing the underestimation or neglect of critical components. In this way, GCDG excels in capturing the nuances of domain-specific information characterized by diverse distributions. GCDG demonstrates the potential to reduce the target risk and encourage flat minima, improving the model’s generalizability. Extensive experiments show GCDG’s comparable performance on five DG benchmarks and one face anti-spoofing dataset, seamlessly integrating into existing DG methods with consistent improvements. Code will be avail

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Self-Ensembling Semi-Supervised Model for Bone X-ray Images Landmark Detection

Self-Ensembling Semi-Supervised Model for Bone X-ray Images ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian Bai Shenyao Liu Yuzhao Wang Yu Wang Dong Dong 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 First hospital of Jilin University Changchun China

ISBN: (纸本)9781665429825

Bone image landmark detection plays a vital role in orthopedic diseases diagnosis and analysis. As a promising approach, the data-driven convolutional neural network has been widely applied in landmarks detection. However, the model’s performance relies heavily on numerous high-quality labeled data, which are difficult to access. A practical solution for this issue in bone images landmark detection has not been provided, so we propose a framework of semi-supervised bone images landmark detection encouraged by the recent success of the self-ensembling method. The student and teacher networks share the same structure in our framework, where unlabeled data are utilized by enforcing the prediction consistency of two networks under different perturbations to enhance the network’s performance. The two networks use a mutual learning approach to improve the efficiency of using unlabeled data. In addition, we also propose a transformative perturbation scheme to prevent model overfitting during training and enhance the generalization capability of the model on unseen data. Experimental results on an in-house hip dataset collected from the actual process of clinical diagnosis and a publicly available dataset demonstrate that our framework has excellent performance compared with other semi-supervised methods.

关键词： Training Perturbation methods Biological system modeling Predictive models Bones Reliability engineering Data models

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：