检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Yanan Chi, Zhixiang Wang, Yang Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Electrical and Computer Engineering University of Toronto TorontoM5G1V7 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method. Our code is available at https://***/ynanwu/MetaGCD. © 2023, CC0.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Multi-view Intent Learning and Alignment with Large Langue Models for Session-based Recommendation

引用

ACM Transactions on Information Systems 1000年

作者： Shutong Qiao Wei Zhou Junhao Wen Chen Gao Qun Luo Peixuan Chen Yong Li School of Big Data & Software Chongqing University China School of Big Data & Software Chongqing University China Beijing National Research Center for Information Science and Technology Tsinghua University China Tencent China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University China

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While large language models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for *** address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://***/tsinghua-fib-lab/LLM4SBR.

关键词： Recommender System Session-based Recommendation Large Language Models data Augmentation

来源：评论

学校读者我要写书评

暂无评论

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Boyang Yang Haoye Tian Jiadong Ren Hongyu Zhang Jacques Klein Tegawende Bissyande Claire Le Goues Shunfu Jin School of Information Science and Engineering Yanshan University China School of Computing and Information Systems University of Melbourne Australia School of Big Data and Software Engineering Chongqing University China SnT University of Luxembourg Luxembourg School of Computer Science Carnegie Mellon University USA

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality *** apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

关键词： Program Repair Fine-tuning Large Language Model Open Source

来源：评论

学校读者我要写书评

暂无评论

Theoretical search for possible Au-Si crystal structures using a genetic algorithm

引用

Physical Review B 2017年第13期95卷 134109-134109页

作者： Yue-Hang Dong Wen-Cai Lu Xin Xu Xin Zhao K. M. Ho C. Z. Wang Institute of Theoretical Chemistry Jilin University Changchun Jilin 130021 P. R. China School of Data Science and Software Engineering Qingdao University Qingdao Shandong 266071 P. R. China College of Physics and Laboratory of Fiber Materials and Modern Textile Growing Base for State Key Laboratory Qingdao University Qingdao Shandong 266071 P. R. China Ames Laboratory–U.S. DOE and Department of Physics and Astronomy Iowa State University Ames Iowa 50011 USA

We performed a global search for possible Au-Si crystal structures using a genetic algorithm (GA) combined with density functional theory (DFT) calculations. Two Au-Si structures, Au8Si8 and Au16Si8, were found to be energetically stable and have no imaginary frequencies by phonon calculations. The formation energies of all the studied structures gave a convex hull of the Au-Si system, showing that the most stable composition was Au−Si=1:1 and that the Si-rich structures were much less stable than the Au-rich ones.

关键词： Composition Crystal structure Crystal symmetry Phonons Density functional theory First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

A Secure Federated data-Driven Evolutionary Multi-objective Optimization Algorithm

arXiv

引用

arXiv 2022年

作者： Liu, Qiqi Yan, Yuping Ligeti, Péter Jin, Yaochu Trustworthy and General AI Lab School of Engineering Westlake University China Faculty of Technology Bielefeld University Bielefeld33619 Germany Faculty of Informatics Department of Computeralgebra Eötvös Loránd University Hungary Smart Data Group E-Group ICT Software Zrt Hungary Department of Computer Science University of Surrey Surrey GuildfordGU2 7XH United Kingdom

data-driven evolutionary algorithms usually aim to exploit the information behind a limited amount of data to perform optimization, which have proved to be successful in solving many complex real-world optimization problems. However, most data-driven evolutionary algorithms are centralized, causing privacy and security concerns. Existing federated Bayesian optimization algorithms and data-driven evolutionary algorithms mainly protect the raw data on each client. To address this issue, this paper proposes a secure federated data-driven evolutionary multiobjective optimization algorithm to protect both the raw data and the newly infilled solutions obtained by optimizing the acquisition function conducted on the server. We select the query points on a randomly selected client at each round of surrogate update by calculating the acquisition function values of the unobserved points on this client, thereby reducing the risk of leaking the information about the solution to be sampled. In addition, since the predicted objective values of each client may contain sensitive information, we mask the objective values with Diffie-Hellman-based noise, and then send only the masked objective values of other clients to the selected client via the server. Since the calculation of the acquisition function also requires both the predicted objective value and the uncertainty of the prediction, the predicted mean objective and uncertainty are normalized to reduce the influence of noise. Experimental results on a set of widely used multi-objective optimization benchmarks show that the proposed algorithm can protect privacy and enhance security with only negligible sacrifice in the performance of federated data-driven evolutionary optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Unbiased feature selection in learning random forests for high-dimensional data

Scientific World Journal

引用

Scientific World Journal 2015年第1期2015卷 471371页

作者： Nguyen, Thanh-Tung Huang, Joshua Zhexue Nguyen, Thuy Thi Shenzhen Key Laboratory of High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China University of Chinese Academy of Sciences Beijing 100049 China School of Computer Science and Engineering Water Resources University Hanoi 10000 Viet Nam College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Faculty of Information Technology Vietnam National University of Agriculture Hanoi 10000 Viet Nam

Random forests (RFs) have been widely used as a powerful classification method. However, with the randomization in both bagging samples and feature selection, the trees in the forest tend to select uninformative features for node splitting. This makes RFs have poor accuracy when working with high-dimensional data. Besides that, RFs have bias in the feature selection process where multivalued features are favored. Aiming at debiasing feature selection in RFs, we propose a new RF algorithm, called xRF, to select good features in learning RFs for high-dimensional data. We first remove the uninformative features using p-value assessment, and the subset of unbiased features is then selected based on some statistical measures. This feature subset is then partitioned into two subsets. A feature weighting sampling technique is used to sample features from these two subsets for building trees. This approach enables one to generate more accurate trees, while allowing one to reduce dimensionality and the amount of data needed for learning RFs. An extensive set of experiments has been conducted on 47 high-dimensional real-world datasets including image datasets. The experimental results have shown that RFs with the proposed approach outperformed the existing random forests in increasing the accuracy and the AUC measures. © 2015 Thanh-Tung Nguyen et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mask R-CNN with R-D Net: A Detection and Segmentation Model for Early Gastric Cancer Gastroscopy Images 3

Mask R-CNN with R-D Net: A Detection and Segmentation Model ...

引用

3rd International Conference on Electronic Information engineering and Computer science, EIECS 2023

作者： Liang, Tao Lei, Yi Song, Wenai Sun, Xue Du, Jun Wang, Qing Zhao, Li North University of China School of Software Engineering Taiyuan China Beijing University of Technology Faculty of Information Technology Beijing China Chinese Academy of Medical Sciences Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Vip Department Family Medicine Department Beijing China Chinese Academy of Medical Sciences Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Department of Pathology Beijing China Cross-Strait Tsinghua Research Institute Pharmacovigilance Research Center for Information Technology and Data Science Xiamen China Tsinghua University Department of Automation Beijing China Chinese Academy of Medical Sciences Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Department of Gastroenterology Beijing China

ISBN: (纸本)9798350316674

Gastric cancer is one of the most common malignant tumors of the digestive system. Although gastroscopy can effectively detect early cancers, manual identification and diagnosis is time-consuming and laborious, and the false-negative rate is as high as 4.6-25.8%. Early gastric cancer lesion areas can be detected and segmented using deep learning techniques. We collected and organized 12665 eligible gastroscopy images, and cropped and expanded the original dataset after labeling by professional doctors, and finally obtained 19673 images for model training. We propose ResMSE Net and DWFF Net and apply these two networks to Mask R-CNN to obtain a new model: Mask R-CNN With R-D Net. On the same standard dataset, the mAP@[IoU=0.5] and ACC values of the Mask R-CNN With R-D Net model achieve respectively 45.37% and 67.74%, which are improved by 5.83% and 9.08%, respectively, compared with the original model. In our experiments, we found that Mask R-CNN With R-D Net is difficult to detect targets that are extremely similar to the background, which is the direction of our future work. Secondly, we hope to minimize the number of model parameters and make the model more lightweight under the premise of ensuring accuracy, so that the model can be embedded into gastroscopy detection equipment for real-time detection. © 2023 IEEE.

关键词： deep learning early gastric cancer gastroscopy images

来源：评论

学校读者我要写书评

暂无评论

Effects of Phytohormone Compatibility on Callus Growth of Rosa rugosa tunb

引用

IOP Conference Series: Earth and Environmental science 2020年第3期446卷

作者： Wenbo Chang Xue Wang Ying Lan Meini Wang Bin Wen Lan Li College of Science Jiamusi University Jiamusi City Heilongjiang Province 154007 China School of Data Science and Software Engineering Wuzhou University Wuzhou City Guangxi Province 543000 China

To obtain superior quality callus and to regenerate root system of Rosa rugosa tunb and improve culture efficiency, this experiment used a multi-factor orthogonal test method to establish a sterile system with young leaves of R. rugosa tunb as experimental materialsand different concentrations of hormones in each stage. Explore the effects of plant callus growth. The results showed that the optimal disinfection method of explants was 70% alcohol 30s+0.1% HgCl2 8min. At this time, the browning rate was 46.70%, and the infection rate was 10.00%, which was 14.40% and 72.67% lower than that before disinfection. [Primary medium]: MS+1.5 mg/L 6-BA+3.0 mg/L NAA+3% sucrose+0.9% agar, the induction rate at this time is 75.00%, an increase of 62.50% compared with no added hormone. [Proliferation medium] MS+2.0mg/L 6-BA+0.2mg/L NAA+3% sucrose+0.9% agar, the callus diameter reached 2.49cm after proliferation, the growth was strong, and the callus was highly available. [Rooting medium] MS+0.4mg/L IBA+0.5g/L AC+3% sucrose+ 0.9% agar, the rooting rate is 75.00%, the root system is long and the growth is robust.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on Assessment Methods of Developmental Coordination Disorder in Children

Study on Assessment Methods of Developmental Coordination Di...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Wen-Bo Cui Wen-Ai Song Zi-Tong Pei Yi Lei Qing Wang Yan-Jie Chen Ji-Jiang Yang School of Software Engineering North University of China Taiyuan China Faculty of Information Technology Beijing University of Technology Beijing China Department of Automation Tsinghua University Beijing China Department of Children’s Health Care Centre Beijing Children’s Hospital Capital Medical University Beijing China Pharmacovigilance Research Center for Information Technology and Data Science Cross-Strait Tsinghua Research Institute Xiamen China

Poor fine motor performance is an important feature of children's developmental coordination disorder. To improve the diagnosis efficiency of developmental coordination disorder, computer vision-based evaluation methods have become a research hot topic. Most of the current methods are based on the evaluation of artificial features, while this paper proposes an automatic evaluation method of children's fine movements based on deep learning. By extracting human key points from videos, the method extracts the time series features of key points and uses deep learning neural networks to classify and predict children's fine movements. The experimental results show that the highest accuracy of this method is 81%, which provides an effective tool for the auxiliary diagnosis of children's developmental coordination disorder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explore the designated frequency band (EMF) effect of radiation on biological characteristics of Ocimum basilicum

引用

IOP Conference Series: Earth and Environmental science 2020年第3期446卷

作者： Yaosheng Zhang Guoli Ren Wu Zhang Jiali Yang Xue Wang Yi Chu Lan Li College of Science Jiamusi University Jiamusi City Heilongjiang Province 154007 China School of Data Science and Software Engineering Wuzhou University Wuzhou City Guangxi Province 543000 China

Explore and obtain the effects of irradiated Ocimum basilicum seeds on the biological mechanisms of germination and seedling growth in the specified frequency bands. In the experiment, two influencing factors of the specified frequency band and irradiation time were set, and different gradients of irradiated seeds were set. Non-magnetized treatment was used as a blank control group (CK) to determine the changes in the main chemical components in seeds and seedlings, and explore the radiation breeding biology mechanism. The results showed that 90 kHz-100 kHz had a significant inhibitory effect on seed germination, and the 50 kHz-70 kHz band had a significant effect on the germination of Ocimum basilicum, with 50 ± 2.0 kHz being the best. In the time gradient exploration, the main chemical content of seeds was the highest when irradiated for 20 min, and the growth effect of seedlings was the best. The specified frequency band (EMF) has the effect of promoting and inhibiting the germination and growth of basil. It stimulates the internal chemical composition to break the dormancy period of the seed, accelerates the anabolism, and increases the molecular assimilation of the building.

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：