检索结果-内蒙古大学图书馆

2021年第三届先进计算机技术、信息科学与通信国际会议(CTISC2021)

作者： Weixin Tan Dandan Song Yujin Gao Lab of High Volume language Information Processing & Cloud Computing Beijing Lab of Intelligent Information TechnologyBeijing Institute of Technology

ISBN: (纸本)9781665418683

Multi-turn conversation response selection aims to choose the best response from multiple candidates based on matching it with the dialogue context. Mostly, a response full of context-related information tends to be a proper ***, in some cases, a brief response like "ok" could be the more appropriate one. We find that it is a semantically ended conversation that a brief response usually comes after,so there is no need to provide any context-related information after that. Thus, in addition to match the response with context,it is also critical to recognize the state of whether a dialogue has ended, and learn how to get necessary information from context of different end states separately. To achieve this, we propose an end states guided matching network to determine and incorporate the end states by jointly consider the length of response and the local similarity between the response and last few utterances. In addition, we adopt multiple descriptive sequence representations for a more reliable matching *** results demonstrate that our model outperforms the state-of-the-art methods in multiple datasets.

关键词： Information science Computational modeling Computer network reliability Reliability Data mining

来源：评论

学校读者我要写书评

暂无评论

Trajectory diffusion for objectgoal navigation 24

Trajectory diffusion for objectgoal navigation

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xinyao Yu Sixian Zhang Xinhang Song Xiaorong Qin Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing and University of Chinese Academy of Sciences Beijing Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing and University of Chinese Academy of Sciences Beijing and Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (纸本)9798331314385

Object goal navigation requires an agent to navigate to a specified object in an unseen environment based on visual observations and user-specified goals. Human decision-making in navigation is sequential, planning a most likely sequence of actions toward the goal. However, existing ObjectNav methods, both end-to-end learning methods and modular methods, rely on single-step planning. They output the next action based on the current model input, which easily overlooks temporal consistency and leads to myopic planning. To this end, we aim to learn sequence planning for ObjectNav. Specifically, we propose trajectory diffusion to learn the distribution of trajectory sequences conditioned on the current observation and the goal. We utilize DDPM and automatically collected optimal trajectory segments to train the trajectory diffusion. Once the trajectory diffusion model is trained, it can generate a temporally coherent sequence of future trajectory for agent based on its current observations. Experimental results on the Gibson and MP3D datasets demonstrate that the generated trajectories effectively guide the agent, resulting in more accurate and efficient navigation. The code is available at https://***/sx-zhang/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task Prioritization in Multiagent Environments: A Novel Approach Using Nash Q-Learning

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Kexin Hu, Yu Wang, Jielei Li, Lin Zhang, Shuyuan Luo, Guangchun Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China College of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

—With the rapid proliferation of smartphones and various terminal devices, edge computing has gained increasing importance in overcoming computational limitations and enhancing service quality through task offloading. However, most existing approaches handle tasks on a first-come, first-served basis, neglecting task prioritization, which is critical in real-world scenarios where tasks have different levels of urgency and resource requirements. This paper addresses the challenge of effective task prioritization in multi-agent task offloading by proposing a Nash Q-learning-based strategy. Our methodology involves optimizing task allocation decisions using Nash Q-learning to integrate Nash equilibrium principles, thereby enhancing adaptability and dynamic decision-making capabilities within a multi-agent environment. The proposed algorithm is evaluated through extensive simulations, comparing total delay, resource utilization, and task success rates across various task offloading strategies. The results demonstrate that our Nash Q-learning approach outperforms conventional techniques by dramatically lowering overall latency, optimizing resource allocation, and maintaining high task success rates. This work demonstrates the efficacy of Nash Q-learning for dynamically setting priorities for tasks in multi-agent edge computing environments, providing a robust framework for effective resource management and collaborative task completion. And also highlight the potential of Nash Q-learning in advancing intelligent task management in edge computing, suggesting its applicability in real-world, resource-constrained environments. © 2025 IEEE. All rights reserved,

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Why Not Look One Step Ahead in Reinforcement Learning Based Knowledge Graph Reasoning?

SSRN

引用

SSRN 2024年

作者： Wang, Hao Song, Dandan Wu, Zhijing Tian, YuHang Xu, Jing Laboratory of High-Volume Language Information Processing and Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

Multi-hop reasoning is an effective and explainable method for query answering to improve interpretability by finding reasoning paths over knowledge graphs (KGs). Recent studies apply reinforcement learning-based (RL-based) methods with policy agents to solve this problem. However, they only focus on the sequential reasoning paths and the candidate nodes regardless of the local information of adjacency subgraphs and the semantic correlations between relations in every decision step. In this paper, we propose an RL-based multi-hop reasoning model, Look One Step Ahead (LOSA), which regards more expressive adjacency subgraphs rather than nodes as candidate actions and pays attention to the semantic correlations between relations. Specifically, an adjacency aggregation module encodes the information of subgraphs and transmits the encoding to the policy network to help make decisions, which can reduce backtracking and alleviate sparse-reward issues. Furthermore, a semantic matching module is designed to stress the semantic correlations of relations to improve the rationality of the reasoning paths. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed approach. © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Online Midgress-Sensitive Traffic Allocation for Percentile Charging in Pracitcal CDNs 31

Online Midgress-Sensitive Traffic Allocation for Percentile ...

引用

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

作者： Zhan, Huiyou Tan, Haisheng Xu, Huang Zhang, Chi Ni, Hongqiu Zhang, Pengfei Shan, Weihua Li, Xiang-Yang University of Science and Technology of China Cas Key Lab of Wireless-Optical Communications China USTC-Deqing Alpha Innovation Research Institute Zhejiang China Huawei Cloud Computing Technologies Co. Ltd. Algorithm Innovation Lab Xi'an China

ISBN: (纸本)9798350399738

The traffic bandwidth costs comprise a significant amount of operating expenditure in CDNs, induced by the traffic from the end-users to edge servers (edge cost) and from the edge to the center servers (midgress cost). Traffic allocation is the main approach to minimizing the total bandwidth cost. The joint optimization of the total costs is challenging, specifically when the percentile charging mechanism as well as some other practical issues are considered, such as the dynamicity of midgress traffic and the granularity of traffic allocation. In this work, based on our novel miss ratio prediction mechanism, we propose the first online framework, named Iris, jointly optimizing the edge and midgress costs under the 95th percentile charging in commercial CDNs. Iris can theoretically achieve a competitive ratio of 1+pe pc, when the miss ratio of all domains is set as b. Here pe and pc are the unit bandwidth price of the edge and midgress cost, respectively. Iris is tolerant to prediction errors which can be deployed in practical CDN systems. Extensive experiments based on real data indicate that Iris can dramatically reduce bandwidth costs by about 8.149% compared with the SOTA schemes, potentially saving millions of dollars per month for our large-scale commercial CDN collaborator. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (AI) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,AI is playing an important ***,although AI is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization

Domain-aware Node Representation Learning for Graph Out-of-D...

引用

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

作者： Yi Qiao Yang Liu Qing He Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciencs Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.

关键词： Representation learning Training Degradation Interpolation Correlation Training data Signal processing Graph neural networks Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures 23

FlexiFed: Personalized Federated Learning for Edge Clients w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Chen, Chunyang Huang, Faliang Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia Faculty of Information Technology Monash University Australia Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed;and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised 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：