检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yan, Guochen Xie, Luyuan Gao, Xinyi Zhang, Wentao Shen, Qingni Fang, Yuejian Wu, Zhonghai School of Computer Science Peking University Beijing China School of Software and Microelectronics Peking University Beijing China PKU-OCTA Laboratory for Blockchain and Privacy Computing Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China The University of Queensland Brisbane Australia Center for Machine Learning Research Peking University Beijing China

ISBN: (纸本)157735897X

Federated learning has become a promising solution for collaboration among medical institutions. However, data owned by each institution would be highly heterogeneous and the distribution is always non-independent and identical distribution (non-IID), resulting in client drift and unsatisfactory performance. Despite existing federated learning methods attempting to solve the non-IID problems, they still show marginal advantages but rely on frequent communication which would incur high costs and privacy concerns. In this paper, we propose a novel federated learning method: Federated learning via Valuable Condensed Knowledge (FedVCK). We enhance the quality of condensed knowledge and select the most necessary knowledge guided by models, to tackle the non-IID problem within limited communication budgets effectively. Specifically, on the client side, we condense the knowledge of each client into a small dataset and further enhance the condensation procedure with latent distribution constraints, facilitating the effective capture of high-quality knowledge. During each round, we specifically target and condense knowledge that has not been assimilated by the current model, thereby preventing unnecessary repetition of homogeneous knowledge and minimizing the frequency of communications required. On the server side, we propose relational supervised contrastive learning to provide more supervision signals to aid the global model updating. Comprehensive experiments across various medical tasks show that FedVCK can outperform state-of-the-art methods, demonstrating that it’s non-IID robust and communication-efficient. © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Deep attentive belief propagation: integrating reasoning and learning for solving constraint optimization problems 22

Deep attentive belief propagation: integrating reasoning and...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yanchen Deng Shufeng Kong Caihua Liu Bo An School of Computer Science and Engineering Nanyang Technological University School of Software Engineering Sun Yat-sen University School of Artificial Intelligence Guilin University of Electronic Technology

ISBN: (纸本)9781713871088

Belief Propagation (BP) is an important message-passing algorithm for various reasoning tasks over graphical models, including solving the Constraint Optimization Problems (COPs). It has been shown that BP can achieve state-of-the-art performance on various benchmarks by mixing old and new messages before sending the new one, i.e., damping. However, existing methods of tuning a static damping factor for BP not only are laborious but also harm their performance. Moreover, existing BP algorithms treat each variable node's neighbors equally when composing a new message, which also limits their exploration ability. To address these issues, we seamlessly integrate BP, Gated Recurrent Units (GRUs), and Graph Attention Networks (GATs) within the message-passing framework to reason about dynamic weights and damping factors for composing new BP messages. Our model, Deep Attentive Belief Propagation (DABP), takes the factor graph and the BP messages in each iteration as the input and infers the optimal weights and damping factors through GRUs and GATs, followed by a multi-head attention layer. Furthermore, unlike existing neural-based BP variants, we propose a novel self-supervised learning algorithm for DABP with a smoothed solution cost, which does not require expensive training labels and also avoids the common out-of-distribution issue through efficient online learning. Extensive experiments show that our model significantly outperforms state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System

History-Aware Hierarchical Transformer for Multi-session Ope...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhang, Tong Liu, Yong Li, Boyang Zeng, Zhiwei Wang, Pengwei You, Yuan Miao, Chunyan Cui, Lizhen School of Computer Science and Engineering Nanyang Technological University Singapore Alibaba-NTU Singapore Joint Research Institute Nanyang Technological University Singapore Joint NTU-UBC LILY Research Centre Nanyang Technological University Singapore Alibaba Group China School of Software Shandong University China

With the evolution of pre-trained language models, current open-domain dialogue systems have achieved great progress in conducting one-session conversations. In contrast, Multi-Session Conversation (MSC), which consists of multiple sessions over a long term with the same user, is under-investigated. In this paper, we propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue. HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses. Specifically, HAHT first encodes history conversation sessions hierarchically into a history memory. Then, HAHT leverages historical information to facilitate the understanding of the current conversation context by encoding the history memory together with the current context with attention-based mechanisms. Finally, to explicitly utilize historical information, HAHT uses a history-aware response generator that switches between a generic vocabulary and a history-aware vocabulary. Experimental results on a large-scale MSC dataset suggest that the proposed HAHT model consistently outperforms baseline models. Human evaluation results support that HAHT generates more human-like, context-relevant and history-relevant responses than baseline models. © 2022 Association for Computational Linguistics.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Strategies for Reducing Polarization in Social Networks

SSRN

引用

SSRN 2022年

作者： Wu, Yue Li, Linjiao Yu, Qiannan Gan, Jiaxin Zhang, Yi School of Computer and Software Engineering Xihua University Chengdu610039 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611730 China School of Economics and Management Yibin University Yibin644000 China

The widespread usage of social networks has intensified the phenomenon of opinion polarization. This polarization has a corrosive effect on the functioning of public opinions, societies, and democracies. Hence, it is vital to devise strategies for reducing polarization. In this paper, we propose a depolarization model based on the modified linear threshold model and the Hegselmann-Krause model. Using this model, we then devise three depolarization strategies (building heterogeneous edges, embedding local neutral opinion, and introducing global neutral opinion), and conduct depolarization experiments with varied parameters, including self-belief parameter, social influence moderating parameter, and the selection mode of new edges and active nodes. Our experiments with synthesized and real-world datasets have yielded some interesting results. © 2022, The Authors. All rights reserved.

关键词： Depolarization

来源：评论

学校读者我要写书评

暂无评论

ASYMMETRIC LOSS FOR POSITIVE-UNLABELED LEARNING

ASYMMETRIC LOSS FOR POSITIVE-UNLABELED LEARNING

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Wang, Cong Pu, Jian Xu, Zhi Zhang, Junping Software Engineering Institute East China Normal University China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China School of Computer Science Fudan University China

ISBN: (纸本)9781665438643

Positive-unlabeled (PU) learning is a learning paradigm when only positive and unlabeled data are available in the training stage. This paradigm is particularly useful for the applications that the negative samples are hard to define or expensive to obtain. We propose a simple yet effective and scalable method to address PU learning with a novel asymmetric loss. The proposed asymmetric loss behaviors differently for the prediction errors of the labeled and unlabeled samples, and thus encourages the identification of the negative examples from the unlabeled set. For the PU learning with SCAR assumption, neither hyper-parameter nor class prior is required to be tuned or known. For the situation with selection bias on the labeled samples, we propose a heuristic method to automatically choose the hyper-parameter according to the class prior on the training data. Compared with previous approaches, our method only requires a slight modification of the conventional cross-entropy loss and is compatible with various deep neural networks in an end-to-end way. Extensive experiments on synthetic and real-world datasets with and without SCAR assumption verify the superior performance of the proposed method. © 2021 IEEE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MoMa: A Modular Deep Learning Framework for Material Property Prediction

arXiv

引用

arXiv 2025年

作者： Wang, Botian Ouyang, Yawen Li, Yaohui Wang, Yiqun Cui, Haorui Zhang, Jianbing Wang, Xiaonan Ma, Wei-Ying Zhou, Hao Tsinghua University China Department of Computer Science and Technology Tsinghua University China School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University China Department of Chemical Engineering Tsinghua University China

Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa’s potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning 39

Improving Complex Reasoning over Knowledge Graph with Logic-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy College of Computing and Data Science Nanyang Technological University 639798 Singapore

ISBN: (纸本)157735897X

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Matching Based Joint Trading Contract of Energy and Computation in Virtual Power Plant

Matching Based Joint Trading Contract of Energy and Computat...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yanhui Wang Li Wang Lianming Xu Zemin Sun Kuankuan Sima School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing China College of Computer Science and Technology Jilin University Changchun China

ISBN: (纸本)9781665435413

Electric power grid intelligence and automation are inseparable from the support of computing resources. Electric vehicles (EVs) can provide low-cost and flexible computing offloading services for nearby grid nodes. In this paper, we propose a collaborative model between EVs and intelligent charging stations (CSs) for energy and computation trading, where EVs can contribute their computation resources to CSs during charging at CSs. However, due to selfishness, CSs may refuse to reveal their computing requirements to the EVs, leading to information asymmetry. To cope with this limitation, the contract theory is employed to incentivize interaction between potential CS-EV pair for resource trading. Furthermore, we propose a stable-matching-based algorithm to match CSs and EVs into cooperative groups to achieve mutual-beneficial utilities. Simulation results verify the effectiveness of our algorithm.

关键词： Waste materials Simulation Computational modeling Collaboration Virtual power plants Electric vehicles Power systems

来源：评论

学校读者我要写书评

暂无评论

Advanced Clustering Techniques for Speech Signal Enhancement: A Review and Metanalysis of Fuzzy C-Means, K-Means, and Kernel Fuzzy C-Means Methods

arXiv

引用

arXiv 2024年

作者： Abdullah, Abdulhady Abas Ahmed, Aram Mahmood Rashid, Tarik Veisi, Hadi Rassul, Yassin Hussein Hassan, Bryar Fattah, Polla Ali, Sabat Abdulhameed Shamsaldin, Ahmed S. Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq School of Intelligent Systems College of Interdisciplinary Science and Technologies University of Tehran Iran Computer Science and Engineering Department University of Kurdistan Hewler KR Erbil Iraq Software and Informatics Engineering College of Engineering Salahaddin University-Erbil Iraq

Speech signal processing is a cornerstone of modern communication technologies, tasked with improving the clarity and comprehensibility of audio data in noisy environments. The primary challenge in this field is the effective separation and recognition of speech from background noise, crucial for applications ranging from voice-activated assistants to automated transcription services. The quality of speech recognition directly impacts user experience and accessibility in technology-driven communication. This review paper explores advanced clustering techniques, particularly focusing on the Kernel Fuzzy C-Means (KFCM) method, to address these challenges. Our findings indicate that KFCM, compared to traditional methods like K-Means (KM) and Fuzzy C-Means (FCM), provides superior performance in handling nonlinear and non-stationary noise conditions in speech signals. The most notable outcome of this review is the adaptability of KFCM to various noisy environments, making it a robust choice for speech enhancement applications. Additionally, the paper identifies gaps in current methodologies, such as the need for more dynamic clustering algorithms that can adapt in real time to changing noise conditions without compromising speech recognition quality. Key contributions include a detailed comparative analysis of current clustering algorithms and suggestions for further integrating hybrid models that combine KFCM with neural networks to enhance speech recognition accuracy. Through this review, we advocate for a shift towards more sophisticated, adaptive clustering techniques that can significantly improve speech enhancement and pave the way for more resilient speech processing systems. © 2024, CC BY.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Online Joint Power Allocation and Task Scheduling for LEO Satellite Networks

Online Joint Power Allocation and Task Scheduling for LEO Sa...

引用

IEEE Conference on Wireless Communications and Networking

作者： Zheyuan Li Lijun He Juncheng Wang Ziye Jia Yanting Wang Chau Yuen School of Software Northwestern Polytechnical University China School of Information and Control Engineering China University of Mining and Technology China Department of Computer Science Hong Kong Baptist University China Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics China School of Electrical and Electronics Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The excessive proliferation of Low Earth Orbit (LEO) satellites inescapably bring the explosive growth of space data in LEO Satellite Networks (LSNs). Meanwhile, the stochastic arrivals of space data together with the time-varying satellite-ground links in LSNs pose significant challenges for offloading a large volume of space data from LSNs to ground stations. To circumvent these challenges, we systematically study the energy-constrained online data offloading problem to jointly optimize power allocation and task scheduling for LSNs. First, we leverage Lyapunov optimization to decouple our formulated long-term stochastic joint optimization problem into a set of per-time-slot subproblems. Then, each subproblem is decoupled into a task scheduling problem and a power allocation problem. Next, we derive the optimal solution to the power allocation problem and propose a multi-armed bandit based quasi-optimal solution to the task scheduling problem. Finally, extensive simulation results show that our proposed algorithm has superior performance over the state-of-the-art solutions.

关键词： Space vehicles Satellites Simulation Low earth orbit satellites Scheduling Explosives Resource management Optimization Space stations

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：