检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhou, Qi-Le Ye, Han-Jia Wang, Le-Ye Zhan, De-Chuan National Key Laboratory for Novel Software Technology Nanjing University China Dept of Computer Science School of EECS Peking University China

Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature sets of pre-trained models and the target tasks. In this paper, we propose TABTOKEN, a method aims at enhancing the quality of feature tokens (i.e., embeddings of tabular features). TABTOKEN allows for the utilization of pre-trained models when the upstream and downstream tasks share overlapping features, facilitating model fine-tuning even with limited training examples. Specifically, we introduce a contrastive objective that regularizes the tokens, capturing the semantics within and across features. During the pre-training stage, the tokens are learned jointly with top-layer deep models such as transformer. In the downstream task, tokens of the shared features are kept fixed while TABTOKEN efficiently fine-tunes the remaining parts of the model. TABTOKEN not only enables knowledge transfer from a pre-trained model to tasks with heterogeneous features, but also enhances the discriminative ability of deep tabular models in standard classification and regression tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Sensor Network-Based Data Stream Clustering Algorithm for Pervasive Computing

引用

Chinese Journal of Electronics 2023年第2期18卷 255-258页

作者： Ning Ye Ruchuan Wang Institute of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Department of Information Science Nanjing College for Population Programme Management Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Pervasive computing is characterized by the integration with communication and digital media technology embedded to the people's living space. People can transparently access the digital service anywhere. Wireless sensor networks are a novel technology and have broad application prospects. With the maturity of the wireless sensor networks technology, pervasive computing is becoming a reality. It is become a new technology challenge to process the data streams of sensor networks for pervasive environment efficiently and to find useful knowledge in these data streams. A k-means data stream clustering algorithm based on sensor networks is presented. The main idea of this algorithm is to select the initial centroids according to the aggregation gain of the node, then to cluster the data stream using the average square error. The experimental results are showed that this algorithm is effective and efficient.

关键词： Pervasive computing Performance evaluation Knowledge engineering Wireless sensor networks Sociology Clustering algorithms Media

来源：评论

学校读者我要写书评

暂无评论

A Self-Evolving Framework for Multi-Agent Medical Consultation Based on Large Language Models

A Self-Evolving Framework for Multi-Agent Medical Consultati...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kai Chen Ji Qi Jing Huo Pinzhuo Tian Fanyu Meng Xi Yang Yang Gao State Key Laboratory for Novel Software Technology Nanjing University Nanjing China China Mobile (Suzhou) Software Technology Co. Ltd. Suzhou China School of Computer Engineering and Science Shanghai University Shanghai China China Mobile Research Institute Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a multi-agent approach (SeM-Agents) based on large language models for medical consultations. This framework incorporates various doctor roles and auxiliary roles, with agents communicating through natural language. Using a residual structure, the system conducts multi-round medical consultations based on the patient’s treatment background and symptoms. In the final summary and output stage of the consultation, it utilizes two experience databases—the Correct Consultation Experience Database and the Chain of Thought (CoT) Experience Database—which evolve with accumulated experience during consultations. This evolution drives the framework’s self-improvement, significantly enhancing the rationality and accuracy of the consultations. To ensure that the conclusions are safe, reliable, and aligned with human values, the final decisions undergo a safety review before being provided to the patient. This framework achieved accuracy rates of 89.2% and 83.1% on the MedQA and PubMedQA datasets, respectively.

关键词： Accuracy Pollution Databases Reviews Large language models Natural languages Signal processing Safety Reliability Speech processing

来源：评论

学校读者我要写书评

暂无评论

Efficient Routing Protection Algorithm Based on Optimized Network Topology

引用

computers, Materials & Continua 2022年第9期72卷 4525-4540页

作者： Haijun Geng Zikun Jin Jiangyuan Yao Han Zhang Zhiguo Hu Bo Yang Yingije Guo Wei Wang Qidong Zhang Guoao Duan School of Computer and Information Technology Shanxi UniversityShanxi030006China School of Automation and Software Engineering Shanxi UniversityShanxi030006China School of Computer Science and Technology Hainan UniversityHaikou570228China Department of Computer Science&Technology Tsinghua UniversityBeijing100084China Department of Urban&Regional Planning San JoséState University San JoséCA95192USA Key Laboratory of Embedded System and Service Computing(Tongji University) Ministry of EducationShanghai201804China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu610054China Beijinng University of Technology Beijing-Dublin International CollegeBeijing University of TechnologyBeijing100124China

Network failures are unavoidable and occur *** the network fails,intra-domain routing protocols deploying on the Internet need to undergo a long convergence *** this period,a large number of messages are discarded,which results in a decline in the user experience and severely affects the quality of service of Internet Service Providers(ISP).Therefore,improving the availability of intra-domain routing is a trending research question to be *** usually employs routing protection algorithms to improve intra-domain routing ***,existing routing protection schemes compute as many backup paths as possible to reduce message loss due to network failures,which increases the cost of the network and impedes the methods deployed in *** address the issues,this study proposes an efficient routing protection algorithm based on optimized network topology(ERPBONT).ERPBONT adopts the optimized network topology to calculate a backup path with the minimum path coincidence degree with the shortest path for all source ***,the backup path with the minimum path coincidence with the shortest path is described as an integer programming *** the simulated annealing algorithm ERPBONT is used to find the optimal ***,the algorithm is tested on the simulated topology and the real *** experimental results show that ERPBONT effectively reduces the path coincidence between the shortest path and the backup path,and significantly improves the routing availability.

关键词： Routing protection algorithm network availability network failure shortest path backup path

来源：评论

学校读者我要写书评

暂无评论

Automatic Buffer Overflow Warning Validation

引用

Journal of computer science & technology 2020年第6期35卷 1406-1427页

作者： Feng-Juan Gao Yu Wang Lin-Zhang Wang Zijiang Yang Xuan-Dong Li State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China Department of Computer Science Western Michigan UniversityKalamazoo 49008-5466U.S.A.

Static buffer overflow detection techniques tend to report too many false positives fundamentally due to the lack of software execution information. It is very time consuming to manually inspect all the static warnings. In this paper, we propose BovInspector, a framework for automatically validating static buffer overflow warnings and providing suggestions for automatic repair of true buffer overflow warnings for C programs. Given the program source code and the static buffer overflow warnings, BovInspector first performs warning reachability analysis. Then, BovInspector executes the source code symbolically under the guidance of reachable warnings. Each reachable warning is validated and classified by checking whether all the path conditions and the buffer overflow constraints can be satisfied simultaneously. For each validated true warning, BovInspector provides suggestions to automatically repair it with 11 repair strategies. BovInspector is complementary to prior static buffer overflow discovery schemes. Experimental results on real open source programs show that BovInspector can automatically validate on average 60% of total warnings reported by static tools.

关键词： buffer overflow static analysis warning symbolic execution automatic repair

来源：评论

学校读者我要写书评

暂无评论

A Unified Open Adapter for Open-World Noisy Label Learning: Data-Centric and Learning-Based Insights

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Zong, Chen-Chen Yang, Peng-Hui Xie, Ming-Kun Huang, Sheng-Jun Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization College of Computer Science and Technology Nanjing211106 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Tokyo103-0027 Japan

Noisy label learning (NLL) in open-world scenarios poses a novel challenge due to the presence of noisy data from both known and unknown classes. Most existing methods operate under the closed-set assumption, rendering them vulnerable to open-set noise, which significantly degrades their performance. While some approaches attempt to mitigate the impact of open-set examples, they struggle to learn effective discriminative representations for them, leading to unsatisfactory recognition performance. To address these issues, we propose a unified Open Adapter (OpenAda) that identifies open-set noise from both data-centric and learning-based perspectives, and can be easily integrated into mainstream NLL methods to improve their performance and robustness. Specifically, the data-centric part leverages label clusterability to sequentially identify basic clean and basic open-set examples both with high neighbor agreement. The learning-based part integrates one-vs-all classifiers with a progressive open disambiguation strategy to learn a reliable "inlier vs. outlier" boundary for each class. This enables the model to detect challenging open-set examples that partially overlap in the representation space with closed-set ones. Extensive experiments on synthetic and real-world datasets validate the superiority of our approach. Notably, with minor modifications, DivideMix with OpenAda achieves performance improvements of 9.31% and 18.26% on the open-world CIFAR-80 dataset under 80% symmetric noise and 40% asymmetric noise. The code is available at https://***/chenchenzong/OpenAda. © 2025 IEEE. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Local Search Algorithm for MaxSMT(LIA)

arXiv

引用

arXiv 2024年

作者： He, Xiang Li, Bohan Zhao, Mengyu Cai, Shaowei Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

MaxSAT modulo theories (MaxSMT) is an important generalization of Satisfiability modulo theories (SMT) with various applications. In this paper, we focus on MaxSMT with the background theory of Linear Integer Arithmetic, denoted as MaxSMT(LIA). We design the first local search algorithm for MaxSMT(LIA) called PairLS, based on the following novel ideas. A novel operator called pairwise operator is proposed for integer variables. It extends the original local search operator by simultaneously operating on two variables, enriching the search space. Moreover, a compensation-based picking heuristic is proposed to determine and distinguish the pairwise operations. Experiments are conducted to evaluate our algorithm on massive benchmarks. The results show that our solver is competitive with state-of-the-art MaxSMT solvers. Furthermore, we also apply the pairwise operation to enhance the local search algorithm of SMT, which shows its extensibility. Copyright © 2024, The Authors. All rights reserved.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

arXiv

引用

arXiv 2024年

作者： Qiu, Zi-Hao Guo, Siqi Xu, Mao Zhao, Tuo Zhang, Lijun Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Computer Science and Engineering Texas A&M University College Station United States Computer Science and Engineering Georgia Institute of Technology Atlanta United States

The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs, which is crucial for next token generation, and it scales the similarities in the contrastive loss for training CLIP models. A significant question remains: "Is it viable to learn a neural network to predict a personalized temperature of any input data for enhancing LFMs?" In this paper, we present a principled framework for learning a small yet generalizable temperature prediction network (TempNet) to improve LFMs. Our solution is composed of a novel learning framework with a robust loss underpinned by constrained distributionally robust optimization (DRO), and a properly designed TempNet with theoretical inspiration. TempNet can be trained together with a large foundation model from scratch or learned separately given a pretrained foundation model. It is not only useful for predicting personalized temperature to promote the training of LFMs but also generalizable and transferable to new tasks. Our experiments on LLMs and CLIP models demonstrate that TempNet greatly improves the performance of existing solutions or models, e.g. Table 1. The code to reproduce the experimental results in this paper can be found at https://***/zhqiu/TempNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases

Domain Adaptive Code Completion via Language Models and Deco...

引用

IEEE International Conference on Automated software Engineering (ASE)

作者： Ze Tang Jidong Ge Shangqing Liu Tingwei Zhu Tongtong Xu Liguo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China Nanyang Technological University Singapore Huawei Software Engineering Application Technology China Department of Computer Science Southern Methodist University USA

Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, due to the lack of domain-specific knowledge, they may not be optimal in completing code that requires intensive domain knowledge for example completing the library names. Although there are several works that have confirmed the effectiveness of fine-tuning techniques to adapt language models for code completion in specific domains. They are limited by the need for constant fine-tuning of the model when the project is in constant iteration. To address this limitation, in this paper, we propose $k$ NM-LM, a retrieval-augmented language model (R-LM), that integrates domain knowledge into language models without fine-tuning. Different from previous techniques, our approach is able to automatically adapt to different language models and domains. Specifically, it utilizes the in-domain code to build the retrieval-based database decoupled from LM, and then combines it with LM through Bayesian inference to complete the code. The extensive experiments on the completion of intra-project and intra-scenario have confirmed that $k$ NM-LM brings about appreciable enhancements when compared to CodeGPT and UnixCoder. A deep analysis of our tool including the responding speed, storage usage, specific type code completion, and API invocation completion has confirmed that $k$ NM-LM provides satisfactory performance, which renders it highly appropriate for domain adaptive code completion. Furthermore, our approach operates without the requirement for direct access to the language model's parameters. As a result, it can seamlessly integrate with black-box code completion models, making it easy to integrate our approach as a plugin to further enhance the performance of these models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Class-Aware Prompting for Federated Few-Shot Class-Incremental Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Liang, Fang-Yi Zhan, Yu-Wei Liu, Jiale Zhang, Chong-Yu Chen, Zhen-Duo Luo, Xin Xu, Xin-Shun Shandong University School of Software Jinan250101 China Tsinghua University Department of Computer Science and Technology Beijing100084 China Yunnan Key Laboratory of Software Engineering Kunming650504 China

Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from limited samples while preventing catastrophic forgetting. With the increasing distribution of learning data across different clients and privacy concerns, FSCIL faces a more realistic scenario where few learning samples are distributed across different clients, thereby necessitating a Federated Few-Shot Class-Incremental Learning (FedFSCIL) scenario. However, this integration faces challenges from non-IID problem, which affects model generalization and training efficiency. The communication overhead in federated settings also presents a significant challenge. To address these issues, we propose Class-Aware Prompting for Federated Few-Shot Class-Incremental Learning (FedCAP). Our framework leverages pre-trained models enhanced by a class-wise prompt pool, where shared class-wise keys enable clients to utilize global class information during training. This unifies the understanding of base class features across clients and enhances model consistency. We further incorporate a class-level information fusion module to improve class representation and model generalization. Our approach requires very few parameter transmission during model aggregation, ensuring communication efficiency. To our knowledge, this is the first study to explore the scenario of FedFSCIL. Consequently, we designed comprehensive experimental setups and made the code publicly available. © 2025 IEEE. All rights reserved.

关键词： Federated 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：