检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Zepu Lu Zhongkai Hao Marinka Zitnik Qi Liu Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China and Harvard University Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua Harvard University

The design and optimization of functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepGATGO: A Hierarchical Pretraining-Based Graph-Attention Model for Automatic Protein Function Prediction

arXiv

引用

arXiv 2023年

作者： Li, Zihao Jiang, Changkun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Lab for Big Data System Computing Technology Shenzhen University Shenzhen China

Automatic protein function prediction (AFP) is classified as a large-scale multi-label classification problem aimed at automating protein enrichment analysis to eliminate the current reliance on labor-intensive wet-lab methods. Currently, popular methods primarily combine protein-related information and Gene Ontology (GO) terms to generate final functional predictions. For example, protein sequences, structural information, and protein-protein interaction networks are integrated as prior knowledge to fuse with GO term embeddings and generate the ultimate prediction results. However, these methods are limited by the difficulty in obtaining structural information or network topology information, as well as the accuracy of such data. Therefore, more and more methods that only use protein sequences for protein function prediction have been proposed, which is a more reliable and computationally cheaper approach. However, the existing methods fail to fully extract feature information from protein sequences or label data because they do not adequately consider the intrinsic characteristics of the data itself. Therefore, we propose a sequence-based hierarchical prediction method, DeepGATGO, which processes protein sequences and GO term labels hierarchically, and utilizes graph attention networks (GATs) and contrastive learning for protein function prediction. Specifically, we compute embeddings of the sequence and label data using pre-trained models to reduce computational costs and improve the embedding accuracy. Then, we use GATs to dynamically extract the structural information of non-Euclidean data, and learn general features of the label dataset with contrastive learning by constructing positive and negative example samples. Experimental results demonstrate that our proposed model is no longer limited to specific biological populations and exhibits better scalability in GO term enrichment analysis on large-scale datasets. Copyright © 2023, The Authors. All rights reser

关键词： Gene Ontology

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Pre-trained CNNs and GRU-Based Attention for Image Caption Generation

arXiv

引用

arXiv 2023年

作者： Khan, Rashid Huang, Bingding Hassan, Haseeb Zaman, Asim Ye, Zhongfu University of Science and Technology of China Anhui Hefei230026 China College of Big Data and Internet Shenzhen Technology University Shenzhen518188 China College of Health Sciences and Environmental Engineering Shenzhen Technology University Shenzhen China

Image captioning is a challenging task that involves generating a textual description for an image using both computer vision and natural language processing techniques. In this paper, we propose a deep neural framework for image caption generation using a GRU-based attention mechanism. Our approach employs multiple pre-trained convolutional neural networks as the encoder to extract features from the image and a GRU-based language model as the decoder to generate descriptive sentences. To improve performance, we integrate the Bahdanau attention model with the GRU decoder to enable learning to focus on specific parts of the image. We evaluate our approach using the MSCOCO and Flickr30k datasets and show that it achieves competitive scores compared to state-of-the-art methods. Our proposed framework can bridge the gap between computer vision and natural language and can be extended to specific domains.. Copyright © 2023, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual Information 48

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual Information Pre-trained Language Model

来源：评论

学校读者我要写书评

暂无评论

Pinning synchronization and parameter identification of fractional-order complex-valued dynamical networks with multiple weights

引用

The European Physical Journal B 2022年第8期95卷 1-12页

作者： Ding, Dawei Wang, Ya Hu, Yongbing Yang, Zongli Zhang, Hongwei Zhang, Xu School of Electronics and Information Engineering Anhui University Hefei China National Engineering Research Center for Agro-Ecological Big Data Analysis & Application Anhui University Hefei China China Academy of Information and Communication Technology (CAICT) Beijing China

Compared with single weight networks, multiple weights networks are more practical and universal. Considering the unknown structure and time-varying factor in the actual system, the pinning synchronization of fractional-order complex-valued networks (FCVNs) with unknown parameters and time-varying coupling strength is studied. In addition, according to the identification and adaptive law, the unknown parameters can be identified, and the value of time-varying coupling strength is obtained. Based on fractional-order calculus theory and Lyapunov stability theory, sufficient conditions for pinning synchronization of FCVNs with time-varying coupling strength are derived. Finally, the effectiveness of the pinning controller strategy for fractional-order complex networks is illustrated by two numerical examples in complex-value space.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of pulsed laser biomimetic patterns on surface properties and cell migration of titanium alloys

引用

Surfaces and Interfaces 2025年 68卷

作者： Zhao, Wen Hu, Jun Yu, Zhou Pan, Jiabao School of Mechanical and Automotive Engineering Anhui Polytechnic University Wuhu 241000 China Institute of Artificial Intelligence Donghua University Shanghai 201620 China Shanghai Industrial Big Data Engineering Technology Research Center Shanghai 201620 China

To further investigate the relationship between patterns and cell migration, polar-patterned samples were prepared using an ultraviolet pulsed laser. The effects of the conical structures on the physicochemical properties of the samples were studied through element analysis, roughness, hardness, and wettability characterization. The cell migration behavior on the patterned sample surfaces was analyzed using wound healing experiments. The results show that the laser's impact on the edges of the conical structures is less pronounced than in the central area, resulting in a "spoon-like" feature at the bottom of the microstructure. The plane/cross-sectional profiles of the laser-processed conical structures display gradient changes, forming polar patterns with directional symmetry in shape. The polarization degree of the microstructure determines the diffusion behavior of droplets on the sample surface, affecting wettability in different directions. After immersion in simulated body fluid (SBF), agglomerates and sedimentary layers of the apatite phase form on the sample surface. Due to stress during the drying process, cracks appear in both the laser-processed and non-processed areas. The conical patterns significantly regulate cell migration behavior, with cells exhibiting longer migration distances. The boundary between patterned and non-patterned areas is the main driving force for collective behavior, while the connected pattern boundaries provide greater motility for cells. Among various parameters, the H2# sample (head-to-tail arrangement, height of 200 μm, cone angle of 60°) exhibits the highest cell migration rate at 13.19%. © 2025

关键词： Cell migration Laser processing Polar microstructure Surface performance

来源：评论

学校读者我要写书评

暂无评论

Beamforming design for RIS-aided amplify-and-forward relay networks

引用

Frontiers of Information technology & Electronic engineering 2023年第12期24卷 1728-1738页

作者： Xuehui WANG Feng SHU Riqing CHEN Peng ZHANG Qi ZHANG Guiyang XIA Weiping SHI Jiangzhou WANG School of Information and Communication Engineering Hainan UniversityHaikou570228China School of Electronic and Optical Engineering Nanjing University of Science and TechnologyNanjing210094China Digital Fujian Institute of Big Data for Agriculture Fujian Agriculture and Forestry UniversityFuzhou350002China Institute of Intelligent Agriculture Anhui Agricultural UniversityHefei230036China School of Engineering University of KentCanterburyCT27NTUK

The use of a reconfigurable intelligent surface(RIS)in the enhancement of the rate performance is considered to involve the limitation of the RIS being a passive *** address this issue,we propose a RIS-aided amplify-and-forward(AF)relay network in this *** jointly optimizing the beamforming matrix at AF relay and the phase-shift matrices at RIS,two schemes are put forward to address a maximizing signal-to-noise ratio(SNR)***,aiming at achieving a high rate,a high-performance alternating optimization(AO)method based on Charnes–Cooper transformation and semidefinite programming(CCT-SDP)is proposed,where the optimization problem is decomposed into three subproblems solved using CCT-SDP,and rank-one solutions can be recovered using Gaussian ***,the optimization variables in the CCT-SDP method are matrices,leading to extremely high *** reduce the complexity,a low-complexity AO scheme based on Dinkelbachs transformation and successive convex approximation(DT-SCA)is proposed,where the variables are represented in vector form,and the three decoupling subproblems are solved using *** results verify that compared to three benchmarks(i.e.,a RIS-assisted AF relay network with random phase,an AF relay network without RIS,and a RIS-aided network without AF relay),the proposed CCT-SDP and DT-SCA schemes can harvest better rate ***,it is revealed that the rate of the low-complexity DT-SCA method is close to that of the CCT-SDP method.

关键词： Reconfigurable intelligent surface(RIS) Amplify-and-forward(AF)relay Beamforming Phase shift Semidefinite programming Successive convex approximation

来源：评论

学校读者我要写书评

暂无评论

Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach

arXiv

引用

arXiv 2024年

作者： Wan, Yao Wan, Guanghua Zhang, Shijie Zhang, Hongyu Zhou, Pan Jin, Hai Sun, Lichao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology China University of Leigh United States

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Examples of such models include CodeGPT and StarCoder. These models are typically trained from a large amount of source code collected from open-source communities such as GitHub. Although using source code in GitHub has been a common practice for training deep-learning-based models for code completion, it may induce some legal and ethical issues such as copyright infringement. In this paper, we investigate the legal and ethical issues of current neural code completion models by answering the following question: Is my code used to train your neural code completion model? To this end, we tailor a membership inference approach (termed CodeMI) that was originally crafted for classification tasks to a more challenging task of code completion. In particular, since the target code completion models perform as opaque black boxes, preventing access to their training data and parameters, we opt to train multiple shadow models to mimic their behavior. The acquired posteriors from these shadow models are subsequently employed to train a membership classifier. Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model. We comprehensively evaluate the effectiveness of this adapted approach across a diverse array of neural code completion models, (i.e., LSTM-based, CodeGPT, CodeGen, and StarCoder). Experimental results reveal that the LSTM-based and CodeGPT models suffer the membership leakage issue, which can be easily detected by our proposed membership inference approach with an accuracy of 0.842, and 0.730, respectively. Interestingly, our experiments also show that the data membership of current large language models of code, e.g., CodeGen and StarCoder, is difficult to detect, leaving amper space for further improvement. Finally, we also t

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Caputo -type fractional time-scales Noether theorem of Birkhoffian systems

引用

Acta Mechanica 2022年第11期233卷 4487-4503页

作者： Tian, Xue Zhang, Yi School of Science Nanjing University of Science and Technology Nanjing China School of Mathematics and Big Data Anhui University of Science and Technology Huainan China College of Civil Engineering Suzhou University of Science and Technology Suzhou China

A new type of Noether theorem with Caputo $$\Delta $$ -derivative of Birkhoffian systems is the focus of this paper based upon the fractional time-scales calculus, which constructs a model to unify continuous fractional systems and discrete fractional systems. The Caputo $$\Delta $$ -type fractional time-scales Pfaff-Birkhoff principle is given, and its Birkhoff equations are deduced. According to the definition of fractional time-scales Noether symmetry of Birkhoffian systems, its criterion is proved and its Noether theorem is formulated by the generalized Jost method. Furthermore, the corresponding transformation conditions are given to study the relationship among fractional time-scales Birkhoffian systems, Hamiltonian systems and Lagrangian systems. Taking the fractional time-scales Hojman-Urrutia model as an example, the simulation results show the validity of the new Noether theorem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fast Cell Association Scheme Based on Deep Q-Learning in Ultra-Dense Cellular Networks

引用

China Communications 2021年第2期18卷 259-270页

作者： Jinhua Pan Lusheng Wang Hai Lin Zhiheng Zha Caihong Kai Key Laboratory of Knowledge Engineering with Big Data Ministry of Education.School of Computer Science and Information EngineeringHefei University of TechnologyHefei 230601China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei 230601China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education.School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

To support dramatically increased traffic loads,communication networks become *** cell association(CA)schemes are timeconsuming,forcing researchers to seek fast *** paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is *** the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until *** the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user *** demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional ***,performance metrics,such as capacity and fairness,can be guaranteed.

关键词： ultra-dense cellular networks(UDCN) cell association(CA) deep Q-learning proportional fairness Q-learning

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：