检索结果-内蒙古大学图书馆

PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lan, Yuquan Li, Dongxu Zhang, Yunqi Zhao, Hui Zhao, Gang Software Engineering Institute East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai China Microsoft China

Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts under the zero-shot setting, where the relation sets at the training and testing stages are disjoint. Previous state-of-the-art method handles this challenging task by leveraging pretrained language models to generate data as additional training samples, which increases the training cost and severely constrains the model performance. To address the above issues, we propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation Selection and Entity Boundary Detection. The remarkable characteristic of PCRED is that it does not rely on additional data and still achieves promising performance. The model adopts a relation-first paradigm, recognizing unseen relations through candidate relation selection. With this approach, the semantics of relations are naturally infused in the context. Entities are extracted based on the context and the semantics of relations subsequently. We evaluate our model on two ZeroRTE datasets. The experiment results show that our method consistently outperforms previous works. Our code will be available at https://***/r/PCRED. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

Green Federated Learning Over Cloud-RAN with Limited Fronthual Capacity and Quantized Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Jiali Mao, Yijie Wang, Ting Shi, Yuanming MoE Engineering Research Center of Software/Hardware Co-design Technology and Application The Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai200062 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China

In this paper, we propose an energy-efficient federated learning (FL) framework for the energy-constrained devices over cloud radio access network (Cloud-RAN), where each device adopts quantized neural networks (QNNs) to train a local FL model and transmits the quantized model parameter to the remote radio heads (RRHs). Each RRH receives the signals from devices over the wireless link and forwards the signals to the CS via the fronthaul link. We rigorously develop an energy consumption model for the local training at devices through the use of QNNs and communication models over Cloud-RAN. Based on the proposed energy consumption model, we formulate an energy minimization problem that optimizes the fronthaul rate allocation, user transmit power allocation, and QNN precision levels while satisfying the limited fronthaul capacity constraint and ensuring the convergence of the proposed FL model to a target accuracy. To solve this problem, we analyze the convergence rate and propose efficient algorithms based on the alternative optimization technique. Simulation results show that the proposed FL framework can significantly reduce energy consumption compared to other conventional approaches. We draw the conclusion that the proposed framework holds great potential for achieving a sustainable and environmentally-friendly FL in Cloud-RAN. Copyright © 2023, The Authors. All rights reserved.

关键词： Radio access networks

Effective Entry-Wise Flow for Molecule Generation

学校读者我要写书评

暂无评论

Effective Entry-Wise Flow for Molecule Generation

International Conference on Data engineering

作者： Qifan Zhang Junjie Yao Yuquan Yang Yizhou Shi Wei Gao Xiaoling Wang School of Computer Science and Technology East China Normal University Software Engineering Institute East China Normal University Shanghai Key Laboratory of Trustworthy Computing Department of Chemistry University of Massachusetts Boston University of Michigan Ann Arbor.

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Molecule generation is a critical process in the fields of drug discovery and materials science. Recently, generative models based on normalizing flows have demonstrated significant potential in this domain. These models are particularly suited for handling the symmetrical and complex chemical structures often encountered in molecular datasets. Despite their promising nature, normalizing flow-based models for molecule generation face considerable challenges. The complexity of molecule representation, the rigorous demands of optimization, and the scarcity of training labels in molecular datasets contribute to these difficulties. Additionally, adequately and comprehensively learning the distribution of molecular datasets remains a formidable task. In this paper, we delve into the intricate entry-wise modules in vanilla flows, introducing an effective variation of flow-based models. Our proposed approach innovatively encapsulates affine coupling transformations within normalizing flows. Furthermore, we deconstruct existing invertible flow models, integrating them with newly developed entry-wise transformations. Our experimental studies demonstrate that these proposed entry-wise modules, when incorporated into standard flow-based models, surpass other generative models in performance on various representative datasets and generation tasks. Notably, in the context of low-resourced molecular graph generation, our model achieves remarkable performance compared to its counterparts.

关键词： Training Couplings Materials science and technology Interpolation Data engineering Drug discovery Task analysis

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Nan Wang, Xiaolu Du, Xiao Cai, Puyu Wang, Ting Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education the Shangh ai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China Software Engineering Institute East China Normal University Shanghai200050 China Computer Science Department New York University New YorkNY10012 United States

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients’ specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

CHECKING CONTINUOUS STOCHASTIC LOGIC AGAINST QUANTUM CONTINUOUS-TIME MARKOV CHAINS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mei, Jingyi Xu, Ming Guan, Ji Deng, Yuxin Yu, Nengkun Shanghai Key Lab of Trustworthy Computing East China Normal University China Shanghai Key Lab of Trustworthy Computing & MoE Engineering Research Center of Software/Hardware Co-design Technology and Application East China Normal University China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences China Department of Computer Science Stony Brook University United States

Verifying quantum systems has attracted a lot of interest in the last decades. In this paper, we study the quantitative model-checking of quantum continuous-time Markov chains (quantum CTMCs). The branching-time properties of quantum CTMCs are specified by continuous stochastic logic (CSL), which is famous for verifying real-time systems, including classical CTMCs. The core of checking the CSL formulas lies in tackling multiphase until formulas. We develop an algebraic method using proper projection, matrix exponentiation, and definite integration to symbolically calculate the probability measures of path formulas. Thus the decidability of CSL is established. To be efficient, numerical methods are incorporated to guarantee that the time complexity is polynomial in the encoding size of the input model and linear in the size of the input formula. A running example of Apollonian networks is further provided to demonstrate our method. © 2022, CC BY.

关键词： Stochastic systems

Towards Efficient Workflow Scheduling Over Yarn Cluster Using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Towards Efficient Workflow Scheduling Over Yarn Cluster Usin...

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have available resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

MC/DC Test Case Automatic Generation for Safety-Critical Systems

学校读者我要写书评

暂无评论

MC/DC Test Case Automatic Generation for Safety-Critical Sys...

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Cong Wang Haiying Sun Hui Dou Hongtao Chen Jing Liu Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Software Engineering Institute East China Normal University Shanghai China Huawei Technology Shanghai China

Testing is an essential part of the software development of Safety-Critical Systems (SCSs). Since it can automatically generate test cases using the system requirement models, Model-Based Testing (MBT) is suitable for SCSs. However, most of the existing system modeling languages for SCSs mainly focus on representing functional requirements rather than safety, e.g., SysML. In this paper, we first propose a modeling language, Safety SysML State Machine (S2MSM), to guarantee safety during the requirement modeling stage. Second, we propose a model transformation algorithm to transform the S2MSM model into an intermediate model. Then, we design a time flow operation sequence that simulates the external real-time environment. Finally, we generate test cases from the intermediate model according to the MC/DC criterion and time flow operation sequence. We conduct a case study on a real-world SCS application to demonstrate the effectiveness and efficiency of the proposed approach.

关键词： Resonator filters Transforms software quality Reliability engineering Real-time systems Systems Modeling Language Safety

Asymmetric Group key Agreement Protocol from Short Signatures

学校读者我要写书评

暂无评论

Asymmetric Group Key Agreement Protocol from Short Signature...

International Conference on Computer and Communications (ICCC)

作者： Kunyu Shen Lei Zhang Rui Zhang Qihao Fang Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai China Science and Technology on Communication Security Laboratory Chengdu Sichuan China

Asymmetric group key agreement allows a group of users to negotiate a public encryption key that corresponds to several decryption keys, and each decryption key can only be computed by one group member. This novel notion ensures the confidentiality of communication among group members and allows any external entity to send messages to the group. However, the existing authenticated asymmetric group key agreement protocols are designed in identity-based cryptosystem or certificateless public key cryptosystem, which are not widely deployed. In this paper, we propose an efficient authenticated asymmetric group key agreement protocol. The protocol captures the security of secrecy, known-key security, key-compromise impersonation, unknown key-share and key control while being resistant to active attacks. The security of our protocol is reduced to the k-BDHE problem.

关键词： Resistance Adaptation models Protocols Computational modeling Authentication Public key cryptography Encryption