检索结果-内蒙古大学图书馆

American Control Conference (ACC)

作者： Dejin Ren Taoran Wu Bai Xue State Key Lab. of Computer Science CAS Institute of Software Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

This paper focuses on addressing the problem of computing controlled reach-avoid sets for continuous-time systems modeled by polynomial ordinary differential equations with control inputs in order to ensure the safety and reachability of safety-critical systems. In a controlled reach-avoid set (CRAS), there exists a feedback controller capable of driving the closed-loop system into a target set of desired states while avoiding hazardous regions. The computation of a controlled reach-avoid set can be transformed into a search for a guidance-barrier function in existing literature. However, existing guidance-barrier functions tend to produce conservative CRASs due to certain flaws. To overcome this issue, a new guidance-barrier function is introduced, which generates less conservative CRASs compared to existing ones. Given the inherent nonlinearity associated with searching for guidance-barrier functions in the control setting, an iterative computational approach is proposed. This approach modifies controllers from previous iterations to find these functions and expand CRASs by solving convex optimizations. Finally, numerical results demonstrate the efficiency of our method in generating less conservative CRASs.

关键词： Three-dimensional displays Computational modeling Ordinary differential equations Polynomials Mathematical models Convex functions Safety

来源：评论

学校读者我要写书评

暂无评论

Learning a Mini-Batch Graph Transformer via Two-Stage Interaction Augmentation 27

Learning a Mini-Batch Graph Transformer via Two-Stage Intera...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Li, Wenda Chen, Kaixuan Liu, Shunyu Zheng, Tongya Huang, Wenjie Song, Mingli State Key Laboratory of Blockchain and Security Zhejiang University China School of Software Technology Zhejiang University China Institute of Blockchain and Data Security China Big Graph Center School of Computer and Computing Science Hangzhou City University China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9781643685489

Mini-batch Graph Transformer (MGT), as an emerging graph learning model, has demonstrated significant advantages in semi-supervised node prediction tasks with improved computational efficiency and enhanced model robustness. However, existing methods for processing local information either rely on sampling or simple aggregation, which respectively result in the loss and squashing of critical neighbor information. Moreover, the limited number of nodes in each mini-batch restricts the model’s capacity to capture the global characteristic of the graph. In this paper, we propose LGMformer, a novel MGT model that employs a two-stage augmented interaction strategy, transitioning from local to global perspectives, to address the aforementioned bottlenecks. The local interaction augmentation (LIA) presents a neighbor-target interaction Transformer (NTIformer) to acquire an insightful understanding of the co-interaction patterns between neighbors and the target node, resulting in a locally effective token list that serves as input for the MGT. In contrast, global interaction augmentation (GIA) adopts a cross-attention mechanism to incorporate entire graph prototypes into the target node representation, thereby compensating for the global graph information to ensure a more comprehensive perception. To this end, LGMformer achieves the enhancement of node representations under the MGT paradigm. Experimental results related to node classification on the ten benchmark datasets demonstrate the effectiveness of the proposed method. Our code is available at https://***/l-wd/LGMformer. © 2024 The Authors.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LEARNING WITH LOGICAL CONSTRAINTS BUT WITHOUT SHORTCUT SATISFACTION 11

LEARNING WITH LOGICAL CONSTRAINTS BUT WITHOUT SHORTCUT SATIS...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Zenan Liu, Zehua Yao, Yuan Xu, Jingwei Chen, Taolue Ma, Xiaoxing Lü, Jian State Key Lab of Novel Software Technology Nanjing University China Department of Mathematics The University of Hong Kong Hong Kong Department of Computer Science Birkbeck University of London United Kingdom

Recent studies have explored the integration of logical knowledge into deep learning via encoding logical constraints as an additional loss ***, existing approaches tend to vacuously satisfy logical constraints through shortcuts, failing to fully exploit the *** this paper, we present a new framework for learning with logical ***, we address the shortcut satisfaction issue by introducing dual variables for logical connectives, encoding how the constraint is *** further propose a variational framework where the encoded logical constraint is expressed as a distributional loss that is compatible with the model's original training *** theoretical analysis shows that the proposed approach bears salient properties, and the experimental evaluations demonstrate its superior performance in both model generalizability and constraint satisfaction. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

ExcePy: A Python Benchmark for Bugs with Python Built-in Types 29

ExcePy: A Python Benchmark for Bugs with Python Built-in Typ...

引用

29th IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2022

作者： Zhang, Xin Yan, Rongjie Yan, Jiwei Cui, Baoquan Yan, Jun Zhang, Jian State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China

ISBN: (纸本)9781665437868

As bugs of Python built-in types can cause code crashes, detecting them is critical to the robustness of the software. Researchers have concluded plenty of patterns for the bug causes and applied these patterns in detection tools. But these tools are only evaluated on handcrafted bugs or bugs obtained from QA pages. Because such bugs cannot reflect the complex code structures and various bug types encountered in real-world projects, the evaluation result is untrustworthy when applied to these projects. As a result, a collection of real-world reproducible bugs is essential for tool evaluation and future bug-related research. In this paper, we propose ExcePy, a benchmark for providing bugs of Python built-in types. We collect 180 bugs from the evolution of 15 real-world open-source Python projects on GitHub and then manually build test scripts for bug reproduction. Meanwhile, to improve tool evaluation efficiency, we present a code pruning strategy that can minimize buggy code size while retaining bug reproducibility and apply it to ExcePy to provide simplified buggy code. To demonstrate the benefits of ExcePy, we use three static analyzers and two fuzzers to detect bugs collected in ExcePy. We found that simplified code can significantly reduce running time and avoid many tool crashes, and bugs supplied by ExcePy can reveal limitations of existing tools in reporting real-world bugs. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Active Learning of One-Clock Timed Automata Using Constraint Solving 20th

Active Learning of One-Clock Timed Automata Using Constrain...

引用

20th International Symposium on Automated Technology for Verification and Analysis, ATVA 2022

作者： Xu, Runqing An, Jie Zhan, Bohua State Key Laboratory of Computer Science Institute of Software CAS Beijing China University of Chinese Academy of Sciences Beijing China Max Planck Institute for Software Systems Kaiserslautern Germany

ISBN: (纸本)9783031199912

Active automata learning in the framework of Angluin’s L∗ algorithm has been applied to learning many kinds of automata models. In applications to timed models such as timed automata, the main challenge is to determine guards on the clock value in transitions as well as which transitions reset the clock. In this paper, we introduce a new algorithm for active learning of deterministic one-clock timed automata and timed Mealy machines. The algorithm uses observation tables that do not commit to specific choices of reset, but instead rely on constraint solving to determine reset choices that satisfy readiness conditions. We evaluate our algorithm on randomly-generated examples as well as practical case studies, showing that it is applicable to larger models, and competitive with existing work for learning other forms of timed models. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

DENOISING WITH A JOINT-EMBEDDING PREDICTIVE ARCHITECTURE

arXiv

引用

arXiv 2024年

作者： Chen, Dengsheng Hu, Jie Wei, Xiaoming Wu, Enhua Meituan China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China

Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains underexplored. Conversely, diffusion models have demonstrated significant efficacy in modeling arbitrary probability distributions. In this paper, we introduce Denoising with a Joint-Embedding Predictive Architecture (D-JEPA), pioneering the integration of JEPA within generative modeling. By recognizing JEPA as a form of masked image modeling, we reinterpret it as a generalized next-token prediction strategy, facilitating data generation in an autoregressive manner. Furthermore, we incorporate diffusion loss to model the per-token probability distribution, enabling data generation in a continuous space. We also adapt flow matching loss as an alternative to diffusion loss, thereby enhancing the flexibility of D-JEPA. Empirically, with increased GFLOPs, D-JEPA consistently achieves lower FID scores with fewer training epochs, indicating its good scalability. Our base, large, and huge models outperform all previous generative models across all scales on ImageNet conditional generation benchmarks. Beyond image generation, D-JEPA is well-suited for other continuous data modeling, including video and audio. © 2024, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

On Efficient Packet Batching and Resource Allocation for GPU based NFV Acceleration 31

On Efficient Packet Batching and Resource Allocation for GPU...

引用

31st IEEE/ACM International Symposium on Quality of Service, IWQoS 2023

作者： Zeng, Deze Zhu, Andong Gu, Lin Chen, Quan Guo, Minyi School of Computer Science China University of Geosciences Hubei Wuhan China Nanjing University State Key Lab. for Novel Software Technology Nanjing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350399738

Network Function Virtualization (NFV) has already become an essential technology for improving the scalability and flexibility of modern computer networks. The performance gap has become the main issue that impedes the development of NFV. GPUs, with massive parallel processors, are advocated to accelerate the Virtualized Network Functions (VNFs). However, the special architecture and workflow of GPUs introduce new challenges, especially on the batched processing, and resource allocation. In this paper, we propose GPU-based NFV Acceleration framework (GNFA) with an efficient packet batching and resource allocation solution. Considering the increased latency caused by the accumulation of the GPU kernel invoking overhead, we first invent a latency reduction mechanism called SM Performance Compensation (SPC). A Partition and Adjustment based Batching and Resource Allocation (PABARA) algorithm that jointly considers batch size tuning and GPU thread allocation is also proposed. We have practically implemented GNFA and extensively evaluated its performance on some well-known VNFs. The experiment results show that GNFA can effectively promote the GPU resource utilization and improve the NFV performance in terms of per-packet latency. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Harvesting Event Schemas from Large Language Models 8th

Harvesting Event Schemas from Large Language Models

引用

8th China Conference on Knowledge Graph and Semantic Computing, CCKS 2023

作者： Tang, Jialong H., Lin Z., Li Y., Lu X., Han L., Sun Chinese Information Processing Laboratory Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819972234

Event schema provides a conceptual, structural and formal language to represent events and model the world event knowledge. Unfortunately, it is challenging to automatically induce high-quality and high-coverage event schemas due to the open nature of real-world events, the diversity of event expressions, and the sparsity of event knowledge. In this paper, we propose a new paradigm for event schema induction – knowledge harvesting from large-scale pre-trained language models, which can effectively resolve the above challenges by discovering, conceptualizing and structuralizing event schemas from PLMs. And an Event Schema Harvester (ESHer) is designed to automatically induce high-quality event schemas via in-context generation-based conceptualization, confidence-aware schema structuralization and graph-based schema aggregation. Empirical results show that ESHer can induce high-quality and high-coverage event schemas on varying domains. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Planning with Linear Temporal Logic Specifications: Handling Quantifiable and Unquantifiable Uncertainty

arXiv

引用

arXiv 2025年

作者： Yu, Pian Li, Yong Parker, David Kwiatkowska, Marta United Kingdom Department of Computer Science University of Oxford United Kingdom Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China

This work studies the planning problem for robotic systems under both quantifiable and unquantifiable uncertainty. The objective is to enable the robotic systems to optimally fulfill high-level tasks specified by Linear Temporal Logic (LTL) formulas. To capture both types of uncertainty in a unified modelling framework, we utilise Markov Decision Processes with Set-valued Transitions (MDPSTs). We introduce a novel solution technique for the optimal robust strategy synthesis of MDPSTs with LTL specifications. To improve efficiency, our work leverages limit-deterministic Büchi automata (LDBAs) as the automaton representation for LTL to take advantage of their efficient constructions. To tackle the inherent nondeterminism in MDPSTs, which presents a significant challenge for reducing the LTL planning problem to a reachability problem, we introduce the concept of a Winning Region (WR) for MDPSTs. Additionally, we propose an algorithm for computing the WR over the product of the MDPST and the LDBA. Finally, a robust value iteration algorithm is invoked to solve the reachability problem. We validate the effectiveness of our approach through a case study involving a mobile robot operating in the hexagonal world, demonstrating promising efficiency gains. © 2025, CC BY.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Sufficient and Necessary Barrier-like Conditions for Safety and Reach-avoid Verification of Stochastic Discrete-time Systems

arXiv

引用

arXiv 2024年

作者： Xue, Bai Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

In this paper, we examine sufficient and necessary barrier-like conditions for the safety verification and reach-avoid verification of stochastic discrete-time systems. Safety verification aims to certify the satisfaction of the safety property, which stipulates that the probability of the system, starting from a specified initial state, remaining within a safe set is greater than or equal to a specified lower bound. A sufficient and necessary barrier-like condition is formulated for safety verification. In contrast, reach-avoid verification extends beyond safety to include reachability, seeking to certify the satisfaction of the reach-avoid property. It requires that the probability of the system, starting from a specified initial state, reaching a target set eventually while remaining within a safe set until the first hit of the target, is greater than or equal to a specified lower bound. Two sufficient and necessary barrier-like conditions are formulated under certain assumptions. These conditions are derived via relaxing Bellman equations. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

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：