检索结果-内蒙古大学图书馆

A resilient generative model in few-shot question answering

Knowledge-Based Systems 2025年 323卷

作者： Zou, Anqi Chen, Yanping Huang, Ruizhang Qin, Yongbin Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang Guizhou550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou550025 China College of Computer Science and Technology Guizhou University Guiyang550025 China

In few-shot question answering (QA), only a limited number of training cases are available to tune pre-trained language models (PLMs) for fitting to the task objective. Because a PLM often contains a large number of parameters optimized by a pretraining objective, it is difficult to bridge the gap between the two optimization objectives with a few training cases, which leads to the overfitting problem. Furthermore, in the decoding process of a generative model, sometimes rebuilding an answer to a question is more challenging than directly choosing from an input, because the ability to rebuild requires more informative knowledge and may generate hallucinatory outputs. Motivated by the above discussions, we propose a resilient deep model to support the few-shot question answering tasks. Instead of ambitiously optimizing a full generative model with a few training cases, the resilient model contains a partial learning module and an answer choosing module to reduce the problems caused by a lack of training cases. This has the advantage to enhance the few-shot learning in question answering. Our method was evaluated using several few-shot QA public evaluation datasets. It achieves a state-of-the-art performance, considerably outperforming related works. © 2025 Elsevier B.V.

关键词： Answer choosing Few-shot question answering Overfitting Partial learning The resilient model

来源：评论

学校读者我要写书评

暂无评论

ProtCLIP: Function-Informed Protein Multi-Modal Learning 39

ProtCLIP: Function-Informed Protein Multi-Modal Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Hanjing Yin, Mingze Wu, Wei Li, Mingyang Fu, Kun Chen, Jintai Wu, Jian Wang, Zheng College of Computer Science and Technology Zhejiang University China State Key Laboratory of Transvascular Implantation Devices of The Second Affiliated Hospital Zhejiang University China Alibaba Cloud Computing China School of Artificial Intelligence and Data Science University of Science and Technology of China China AI Thrust Information Hub HKUST Guangzhou China Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence China

ISBN: (纸本)157735897X

Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in various downstream applications. However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm. To address these issues, this paper curates a large-scale protein-text paired dataset called ProtAnno with a property-driven sampling strategy, and introduces a novel function-informed protein pre-training paradigm. Specifically, the sampling strategy determines selecting probability based on the sample confidence and property coverage, balancing the data quality and data quantity in face of large-scale noisy data. Furthermore, motivated by significance of the protein specific functional mechanism, the proposed paradigm explicitly model protein static and dynamic functional segments by two segment-wise pre-training objectives, injecting fine-grained information in a function-informed manner. Leveraging all these innovations, we develop ProtCLIP, a multi-modality foundation model that comprehensively represents function-aware protein embeddings. On 22 different protein benchmarks within 5 types, including protein functionality classification, mutation effect prediction, cross-modal transformation, semantic similarity inference and protein-protein interaction prediction, our ProtCLIP consistently achieves SOTA performance, with remarkable improvements of 75% on average in five cross-modal transformation benchmarks, 59.9% in GO-CC and 39.7% in GO-BP protein function prediction. The experimental results verify the extraordinary potential of ProtCLIP serving as the protein multi-modality foundation model. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights r

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Indirect influence in social networks as an induced percolation phenomenon (vol 119, e2100151119, 2022)

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF scienceS OF THE UNITED stateS OF AMERICA 2022年第24期119卷 e2100151119-e2100151119页

作者： Xie, Jiarong Wang, Xiangrong Feng, Ling Zhao, Jin-Hua Liu, Wenyuan Moreno, Yamir Hu, Yanqing School of Computer Science and Engineering Sun Yat-sen University 510006 Guangzhou China Institute of Future Networks Southern University of Science and Technology 518055 Shenzhen China Peng Cheng Laboratory 518066 Shenzhen China Institute of High Performance Computing A*STAR 138632 Singapore Department of Physics National University of Singapore 117551 Singapore Guangdong Provincial Key Laboratory of Nuclear Science Institute of Quantum Matter South China Normal University 510006 Guangzhou China Guangdong-Hong Kong Joint Laboratory of Quantum Matter Southern Nuclear Science Computing Center South China Normal University 510006 Guangzhou China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University 637371 Singapore Institute for Biocomputation and Physics of Complex Systems University of Zaragoza 50018 Zaragoza Spain Department of Theoretical Physics University of Zaragoza 50018 Zaragoza Spain ISI Foundation 10126 Torino Italy Department of Statistics and Data Science College of Science Southern University of Science and Technology 518055 Shenzhen China

Percolation theory has been widely used to study phase transitions in network systems. It has also successfully explained various macroscopic spreading phenomena across different fields. Yet, the theoretical frameworks have been focusing on direct interactions among nodes, while recent empirical observations have shown that indirect interactions are common in many network systems like social and ecological networks, among others. By investigating the detailed mechanism of both direct and indirect influence on scientific collaboration networks, here we show that indirect influence can play the dominant role in behavioral influence. To address the lack of theoretical understanding of such indirect influence on the macroscopic behavior of the system, we propose a percolation mechanism of indirect interactions called induced percolation. Surprisingly, our model exhibits a unique anisotropy property. Specifically, directed networks show first-order abrupt transitions as opposed to the second-order continuous transition in the same network structure but with undirected links. A mix of directed and undirected links leads to rich hybrid phase transitions. Furthermore, a unique feature of the nonmonotonic pattern is observed in network connectivities near the critical point. We also present an analytical framework to characterize the proposed induced percolation, paving the way to further understanding network dynamics with indirect interactions.

关键词： percolation indirect interactions social network phase transition behavioral contagion

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Covid-19 Via Multi-Layer Multi-Center Graph Attention Network

Diagnosis of Covid-19 Via Multi-Layer Multi-Center Graph Att...

引用

IEEE International Symposium on Biomedical Imaging

作者： Pingkang Li Haijun Lei Xuegang Song Jia Zhao Jialan Tang Yukang Lei Baiying Lei Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China

Coronavirus disease in 2019 (COVID-19) is a global epidemic, which has affected more than billions of people worldwide. Its intelligent diagnosis based on imaging data has attracted lots of attention, but the heterogeneity between datasets renders its diagnosis challenging. To solve this problem, we propose a new multi-layer multi-center graph attention network (MM-GAN) for COVID-19 diagnosis based on computed tomography (CT) data. First, we use the 3D backbone network to extract feature. Second, we construct a multi-layer multi-center map by using extracted features and auxiliary information, which takes into account the heterogeneity between centers. Third, we use graph attention to generate a new graph structure and learn node representation. Finally, we input the multi-layer multi-center graph into the graph convolution to achieve the COVID-19 detection. Experiments on four multi-center datasets show that the framework is effective and outperforms the traditional classification methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On-chip multiphoton Greenberger-Horne Zeilinger state based on integrated frequency combs

引用

Frontiers of physics 2020年第6期15卷 33-41页

作者： Pingyu Zhu Qilin Zheng Shichuan Xue Chao Wu Xinyao Yu Yang Wang Yingwen Liu Xiaogang Qiang Junjie Wu Ping Xu Institute for Quantum Information and State Key Laboratory of High Performance Computing College of ComputerNational University of Defense TechnologyChangsha 410073China National Innovation Institute of Defense Technology AMSBeijing 100071China National Laboratory of Solid State Micro structures and School of Physics Nanjing UniversityNanjing 210093China

One of the most important multipartite entangled states,Greenberger-Horne-Zeilinger state(GHZ),serves as a fundamental resource for quantum foundat ion test,quantum communication and quantum *** increase the number of entangled particles,significant experimental efforts should been invested due to the complexity of optical setup and the difficulty in maintaining the coherence condition for high-fidelity GHZ ***,we propose an ultra-integrated scalable on-chip GHZ state generation scheme based on frequency *** designing several microrings pumped by different lasers,multiple partially overlapped quantum frequency combs are generated to supply as the basis for on-chip polarization-encoded GHZ state with each qubit occupying a certain spectral *** even and odd numbers of GHZ states can be engineered with constant small number of integrated components and easily scaled up on the same chip by only adjusting one of the pumnp *** addition,we give the on-chip design of projection measurement for characterizing GHZ states and show the reconfigurability of the *** proposal is rather simple and feasible within the existing fabrication technologies and we believe it will boost the development of multiphoton technologies.

关键词： quantum information Greenberger-Horne Zeilinger state frequency comb

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Knowledge Graph Completion Based On Gated Attention Unit

Sequence-to-Sequence Knowledge Graph Completion Based On Gat...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Fengge Yi Xiumei Wei Xiaojing Liu Xuesong Jiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5’s proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware multi-modality learning for eye disease screening

arXiv

引用

arXiv 2024年

作者： Zou, Ke Lin, Tian Han, Zongbo Wang, Meng Yuan, Xuedong Chen, Haoyu Zhang, Changqing Shen, Xiaojing Fu, Huazhu National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu610065 China College of Computer Science Sichuan University Chengdu610065 China Joint Shantou International Eye Center Shantou University the Chinese University of Hong Kong Shantou515041 China Medical College Shantou University Shantou515041 China College of Intelligence and Computing Tianjin University Tianjin300350 China Institute of High Performance Computing Agency for Science Technology and Research 138632 Singapore College of Mathematics Sichuan University Chengdu610065 China

Multi-modal ophthalmic image classification plays a key role in diagnosing eye diseases, as it integrates information from different sources to complement their respective performances. However, recent improvements have mainly focused on accuracy, often neglecting the importance of confidence and robustness in predictions for diverse modalities. In this study, we propose a novel multi-modality evidential fusion pipeline for eye disease screening. It provides a measure of confidence for each modality and elegantly integrates the multimodality information using a multi-distribution fusion perspective. Specifically, our method first utilizes normal inverse gamma prior distributions over pre-trained models to learn both aleatoric and epistemic uncertainty for uni-modality. Then, the normal inverse gamma distribution is analyzed as the Student’s t distribution. Furthermore, within a confidence-aware fusion framework, we propose a mixture of Student’s t distributions to effectively integrate different modalities, imparting the model with heavy-tailed properties and enhancing its robustness and reliability. More importantly, the confidence-aware multi-modality ranking regularization term induces the model to more reasonably rank the noisy single-modal and fused-modal confidence, leading to improved reliability and accuracy. Experimental results on both public and internal datasets demonstrate that our model excels in robustness, particularly in challenging scenarios involving Gaussian noise and modality missing conditions. Moreover, our model exhibits strong generalization capabilities to out-of-distribution data, underscoring its potential as a promising solution for multimodal eye disease screening. © 2024, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Bright photon-pair source based on a silicon dual-Mach-Zehnder microring

引用

science China(Physics,Mechanics & Astronomy) 2020年第2期63卷 3-6页

作者： Chao Wu YingWen Liu XiaoWen Gu XinXin Yu YueChan Kong Yang Wang XiaoGang Qiang JunJie Wu ZhiHong Zhu XueJun Yang Ping Xu Institute for Quantum Information and State Key Laboratory of High Performance Computing College of ComputerCollege of Advanced Interdisciplinary StudiesNational University of Defense TechnologyChangsha 410073China Science and Technology on Monolithic Integrated Circuits and Modules Laboratory Nanjing Electronic Devices InstituteNanjing 210016China National Laboratory of Solid State Microstructures and School of Physics Nanjing UniversityNanjing 210093China

Single photons and photon pairs are typically generated by spontaneous parametric down conversion or quantum dots;however,spontaneous four-wave mixing(SFWM)in silicon microring resonators[1]is also an appealing source of entangled photons,offering a strong cavity-enhanced nonlinear interactions while maintaining features,such as compact,simple to fabricate,and allowing for thermal ***,silicon ring-resonators usually suffer from a trade-off between providing a high pair generation rate(PGR)and high extraction *** achieve high PGR,devices are generally operated with the signal and idler photons in the undercoupling regime and pump photons at the critical coupling point,while high extraction rates require the converted photons to be ***,the optimal conditions for achieving maximal output photon pair flux are critical coupling for the pump photons and overcoupling for the converted photons[2,3].

关键词： coupling photon converted

来源：评论

学校读者我要写书评

暂无评论

Details Enhancement in Unsigned Distance Field Learning for high-fidelity 3D Surface Reconstruction 39

Details Enhancement in Unsigned Distance Field Learning for ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Cheng Hou, Fei Wang, Wencheng Qin, Hong Zhang, Zhebin He, Ying Key Laboratory of System Software (CAS) State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Advanced Interdisciplinary Sciences University of Chinese Academy of Sciences China Department of Computer Science Stony Brook University United States InnoPeak Technology United States College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Cold-Start Link Prediction via Weighted Symmetric Nonnegative Matrix Factorization with Graph Regularization

引用

computer Systems science & Engineering 2022年第12期43卷 1069-1084页

作者： Minghu Tang Wei Yu Xiaoming Li Xue Chen Wenjun Wang Zhen Liu key Laboratory of Artificial Intelligence Application Technology State Ethnic Affairs Commission Qinghai Minzu UniversityXining810007China School of Computer Science Qinghai Minzu UniversityXining810007China College of Intelligence and Computing Tianjin UniversityTianjin300350China School of International Business Zhejiang Yuexiu UniversityShaoxing312069China Law School Tianjin UniversityTianjin300072China Graduate School of Engineering Nagasaki Institute of Applied ScienceNagasaki851-0193Japan

Link prediction has attracted wide attention among interdisciplinaryresearchers as an important issue in complex network. It aims to predict the missing links in current networks and new links that will appear in future *** the presence of missing links in the target network of link prediction studies, the network it processes remains macroscopically as a large connectedgraph. However, the complexity of the real world makes the complex networksabstracted from real systems often contain many isolated nodes. This phenomenon leads to existing link prediction methods not to efficiently implement the prediction of missing edges on isolated nodes. Therefore, the cold-start linkprediction is favored as one of the most valuable subproblems of traditional linkprediction. However, due to the loss of many links in the observation network, thetopological information available for completing the link prediction task is extremely scarce. This presents a severe challenge for the study of cold-start link prediction. Therefore, how to mine and fuse more available non-topologicalinformation from observed network becomes the key point to solve the problemof cold-start link prediction. In this paper, we propose a framework for solving thecold-start link prediction problem, a joint-weighted symmetric nonnegative matrixfactorization model fusing graph regularization information, based on low-rankapproximation algorithms in the field of machine learning. First, the nonlinear features in high-dimensional space of node attributes are captured by the designedgraph regularization term. Second, using a weighted matrix, we associate the attribute similarity and first order structure information of nodes and constrain eachother. Finally, a unified framework for implementing cold-start link prediction isconstructed by using a symmetric nonnegative matrix factorization model to integrate the multiple information extracted together. Extensive experimental validationon five rea

关键词： Link prediction cold-start nonnegative matrix factorization graph regularization

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：