检索结果-内蒙古大学图书馆

Unifying Large Language Models and Knowledge Graphs: A Roadmap

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Shirui Luo, Linhao Wang, Yufei Chen, Chen Wang, Jiapu Wu, Xindong Griffith University QLD Australia The Department of Data Science and AI Monash University Melbourne Australia The Nanyang Technological University Singapore The Faculty of Information Technology Beijing University of Technology Beijing China The Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology Hefei China The Research Center for Knowledge Engineering Zhejiang Lab Hangzhou China

Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolve by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely, 1) KG-enhanced LLMs, which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs;2) LLM-augmented KGs, that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering;and 3) Synergized LLMs + KGs, in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

Reconciling Selective Logging and Hardware Persistent Memory Transaction

学校读者我要写书评

暂无评论

Reconciling Selective Logging and Hardware Persistent Memory...

IEEE Symposium on High-Performance Computer Architecture

作者： Chencheng Ye Yuanchao Xu Xipeng Shen Yan Sha Xiaofei Liao Hai Jin Yan Solihin 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 North Carolina State University Raleigh North Carolina USA University of Central Florida Florida USA

Log creation, maintenance, and its persist ordering are known to be performance bottlenecks for durable transactions on persistent memory. Existing hardware persistent memory transactions overlook an important opportunity for improving performance: some persistent data is algorithmically redundant such that it can be recovered from other data, removing the need for logging such data. The paper presents an ISA extension that enables selective logging for hardware persistent memory transactions for the first time. The ISA extension features two novel components: fine-grain logging and lazy persistency. Fine-grain logging allows hardware to log updates on data in the granularity of words without lengthening the critical path of data accesses. Lazy persistency allows updated data to remain in the cache after the transaction commits. Together, the new hardware persistent memory transaction outperforms the state-of-the-art hardware counterpart by 1.8× on average.

关键词： Computer architecture Maintenance engineering Hardware Optimization IEEE transactions

A nearly optimal distributed algorithm for computing the weighted girth

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第11期64卷 80-94页

作者： Qiang-Sheng HUA Lixiang QIAN Dongxiao YU Xuanhua SHI Hai JIN 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 TechnologyHuazhong University of Science and Technology School of Computer Science and Technology Shandong University

Computing the weighted girth, which is the sum of weights of edges in the minimum weight cycle,is an important problem in network analysis. The problem for distributively computing girth in unweighted graphs has garnered lots of attention, but there are few studies in weighted graphs. In this paper, we propose a distributed randomized algorithm for computing the weighted girth in weighted graphs with integral edge weights in the range [1, nc], where n is the number of vertices and c is a constant. The algorithm is devised under the standard synchronous CON GE S T model, which limits each vertex can only transfer O（log n） bits information along each incident edge in a round. The upper bound of the algorithm is O（n log2n） rounds. We also prove the lower bound for computing the weighted girth is ?（D + n/log n） where D is the hop diameter of the weighted graph. This means our distributed algorithm is optimal within a factor of O（log3n）.

关键词： distributed algorithms weighted girth \({\cal C}{\cal O}{\cal N}{\cal G}{\cal E}{\cal S}{\cal T}\) model communication complexity round complexity

Hierarchical Graph Transformer with Adaptive Node Sampling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Zaixi Liu, Qi Hu, Qingyong Lee, Chee-Kong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong Tencent America United States

The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-structured data, transformers have not achieved competitive performance, especially on large graphs. In this paper, we identify the main deficiencies of current graph transformers: (1) Existing node sampling strategies in Graph Transformers are agnostic to the graph characteristics and the training process. (2) Most sampling strategies only focus on local neighbors and neglect the long-range dependencies in the graph. We conduct experimental investigations on synthetic datasets to show that existing sampling strategies are sub-optimal. To tackle the aforementioned problems, we formulate the optimization strategies of node sampling in Graph Transformer as an adversary bandit problem, where the rewards are related to the attention weights and can vary in the training procedure. Meanwhile, we propose a hierarchical attention scheme with graph coarsening to capture the long-range interactions while reducing computational complexity. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of our method over existing graph transformers and popular GNNs. Our code is open-sourced at https://***/zaixizhang/ANS-GT. © 2022, CC BY-SA.

关键词： Graph theory

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

Estimating Noisy Class Posterior with Part-level labels for Noisy label Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Rui Shi, Bin Ruan, Jianfei Pan, Tianze Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Province Key Lab of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Physics Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China

In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

RGCnet: An Efficient Recursive Gated Convolutional Network for EEG-based Auditory Attention Detection

学校读者我要写书评

暂无评论

RGCnet: An Efficient Recursive Gated Convolutional Network f...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Siqi Cai Jia Li Hongmeng Yang Haizhou Li Department of Electrical and Computer Engineering National University of Singapore Singapore Shien-Ming Wu School of Intelligent Engineering South China University of Technology China Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China Machine Listening Lab University of Bremen Germany

Humans are able to listen to one speaker and disregard others in a speaking crowd, referred to as the "cocktail party effect". EEG-based auditory attention detection (AAD) seeks to identify whom a listener is listening to by decoding one’s EEG signals. Recent research has demonstrated that the self-attention mechanism is effective for AAD. In this paper, we present the Recursive Gated Convolutional network (RGCnet) for AAD, which implements long-range and high-order interactions as a self-attention mechanism, while maintaining a low computational cost. The RGCnet expands the 2nd order feature interactions to a higher order to model the complex interactions between EEG features. We evaluate RGCnet on two public datasets and compare it with other AAD models. Our results demonstrate that RGCnet outperforms other comparative models under various conditions, thus potentially improving the control of neuro-steered hearing devices.

关键词：

Securing Sdn/Nfv-Enabled Campus Networks with Software-Defined Perimeter-Based Zero-Trust Architecture

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Ruambo, Francis A. Zou, Deqing Lopes, Ivandro O. Yuan, Bin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Distributed System Security Wuhan China Hubei Engineering Research Center on Big Data Security Wuhan China National Engineering Research Center for Big Data Technology and System Wuhan China Services Computing Technology and System Lab Wuhan China Cluster and Grid Computing Lab Wuhan China Mbeya university of Science and Technology Mbeya131 Tanzania United Republic of Nucleo Operacional para a Sociedade de Informacao Cape Verde Songshan Laboratory Zhengzhou China

Network softwarization is a breakthrough in designing modern networks and providing numerous new network operations and services. This change is exemplified by Software Defined Networks (SDN) and Network Function Virtualization (NFV). As a result, the combination of SDN and NFV (SDN/NFV) frameworks and individual SDN and NFV frameworks have gained substantial traction in network security over the past decade, significantly supporting on-demand protection measures. However, the inherent security shortcomings of SDN, NFV, and SDN/NFV frameworks provide the fundamental issue in implementing security procedures via network softwarization. To solve this issue, we present a Software-Defined Perimeter (SDP)-powered Zero-Trust Architecture (ZTA) to improve security in the SDN/NFV-enabled campus network holistically. In addition to this, we also propose a threat model and quantitatively assess the suggested approach's performance and security. Furthermore, we highlight potential zero-trust network security function implementations in SDN/NFV-enabled infrastructure to increase protection for endpoint devices, network resources, and flows for detecting threats and responding effectively with minimal latency and overhead. © 2023, The Authors. All rights reserved.

关键词： Access control

Sustainable Self-evolution Adversarial Training

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi’an China

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning