检索结果-内蒙古大学图书馆

Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

Machine Intelligence research 2025年第1期22卷 131-144页

作者： Fenyu Hu Dingshuo Chen Qiang Liu Shu Wu University of Chinese Academy of Sciences Beijing100190China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing100190China

The prediction of molecular properties is a fundamental task in the field of drug ***,graph neural networks(GNNs)have been gaining prominence in this *** a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of ***,limited by expensive and time-consuming human annotations,collecting complete labels for each task is *** a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision *** overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label ***,a bipartite graph is first introduced to model the molecule-task co-occurrence ***,the imputation of missing labels is transformed into predicting missing edges on this bipartite *** predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence *** that,we select reliable pseudo labels according to the uncertainty of the prediction *** with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.

关键词： Graph classification imbalance learning prediction bias mixture of experts multiview representations

来源：评论

学校读者我要写书评

暂无评论

Reward Shaping for Improved Learning in Attacker-Defender Game

引用

Procedia Computer Science 2025年 257卷 158-165页

作者： John Kliem Prithviraj Dasgupta Distributed Intelligent Systems Section Naval Research Laboratory Washington DC 20375 USA

We investigate the effect of reward shaping in improving the performance of reinforcement learning in the context of a real-time strategy game called capture-the-flag. The game is characterized by sparse rewards that are associated with infrequently occurring events such as grabbing or capturing the fag, or tagging the opponent player. We show that appropriately designed reward shaping functions applied to different game events can significantly improve the player’s performance and training times of the player’s learning algorithm. We have validated our reward shaping functions within a simulated environment for playing a marine capture-the-flag game between two players. Our experimental results demonstrate that reward shaping can be used as an effective means to understand the importance of different sub-tasks during game-play towards winning the game, to encode a secondary objective functions such as energy efficiency into a player’s game-playing behavior, and, to improve learning generalizable policies that can perform well against different skill levels of the opponent.

关键词： competitive multi-agent based systems reinforcement learning reward shaping adversarial game

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for Minimizing the Kirchhoff Index via Adding Edges

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3342-3355页

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China School of Computing Australian National University CanberraACT2601 Australia Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges. © 2025 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Retrieval-Augmented Generation Powered by a Multi-agent System to Assisted the Operation of Industries 22nd

Retrieval-Augmented Generation Powered by a Multi-agent Syst...

引用

22nd International Conference on Practical Applications of Agents and Multi-Agent systems, PAAMS 2024

作者： Oliveira, Francisco Gomes, Luis Vale, Zita GECAD – Research Group on Intelligent Engineering and Computing for Advancement Innovation and Development Polytechnic of Porto Porto Portugal LASI – Intelligent Systems Associate Laboratory Polytechnic of Porto Porto Portugal

ISBN: (纸本)9783031704147

The introduction of large language models in recent years transformed the use of artificial intelligence in our daily life, making it available to common users and allowing them to interact with natural language processing machines. However, the common and general knowledge of large language models is not reliable when it comes to the quality of the response and its veracity. The proposed work integrates the use of retrieval-augmented generation with large language models with a multi-agent system framework to enable the creation of trees of knowledge where multiple agents have domain specific knowledge. The proposed agent-based solution was tested in a realistic case study where multiple knowledge domains are distributed amongst six different agents. The case study evaluates the capacity of agents to delegate questions according to its topics and the capacity of correctly replying to questions. The results are promising, demonstrating the ability of large language models to assess and process information that wasn’t used in its training process. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Retrieval-Augmented Generation Based Assistant: A Smart Home Case Study 23rd

Retrieval-Augmented Generation Based Assistant: A Smart Home...

引用

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Ribeiro, Bruno Gomes, Luis Vale, Zita GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Rua Dr. António Bernardino de Almeida 431 Porto4249-015 Portugal

ISBN: (纸本)9783031734991

Smart homes are starting to become more present in our daily lives. Smart homes are useful for enabling energy management services and reducing monetary costs of the consumers. Despite the increasing research in these aspects of the smart home, few actually have in mind the interactivity of the system they propose. Therefore, this paper, an extension of a previous work, proposes a new human-machine interface based on multi-agent systems and natural language models with retrieval-augmented generation techniques for smart homes to facilitate the consumers adaptation to this type of systems. The assistant enables the user to control the house and provides him with the information he needs, even when a problem within the system occurs. Through the experiment the assistant showed to be flexible, able to provide answers to questions outside of the smart home system domain and it increases the scalability of the system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Large Language Models for Multi-agent systems: A Comparative Analysis of AutoGen, CrewAI, and TaskWeaver 22nd

Benchmarking Large Language Models for Multi-agent Systems: ...

引用

22nd International Conference on Practical Applications of Agents and Multi-Agent systems, PAAMS 2024

作者： Barbarroxa, Rafael Gomes, Luis Vale, Zita GECAD – Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI – Intelligent Systems Associate Laboratory Polytechnic of Porto R. Dr. António Bernardino de Almeida 431 Porto4249-015 Portugal

ISBN: (纸本)9783031704147

This paper presents the benchmarking of three multi-agent systems powered by large language models. The paper presents a comparative analysis of AutoGen, CrewAI, and TaskWeaver. Nowadays, large language models have emerged as powerful tools able to assist users in various areas. The integration of large language models into multi-agent systems increases their potential for collaborative problem-solving. This study focuses on a case study involving a machine learning code generation task which is used to evaluate the framework’s performance. To assess the performance of the solutions, it is requested to create energy forecasting models using the same dataset as the base. After producing the code, a new dataset is used to test the model performance using the root mean square error. The three solutions were able to provide results using multiple large language models. The best result was achieved by TaskWeaver using GPT-3.5, with an error of 25.04. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Smart Contract-Based Peer-to-Peer Energy Trading System 6th

A Smart Contract-Based Peer-to-Peer Energy Trading System

引用

6th International Congress on Blockchain and Applications, BLOCKCHAIN 2024

作者： Abbasi, Mahmoud Faria, Pedro Gomes, Luis Prieto, Javier Vale, Zita BISITE Research Group University of Salamanca Salamanca37007 Spain GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Rua Dr. António Bernardino de Almeida 431 Porto4249-015 Portugal

ISBN: (纸本)9783031819278

The transition toward sustainable and decentralized energy systems has prompted the emergence of Peer-to-Peer (P2P) energy trading systems, challenging traditional centralized models. This paper proposes a smart contract-based P2P energy trading system to foster a resilient and sustainable energy ecosystem. By integrating blockchain technology with P2P energy trading, we introduce trust, security, and transparency into energy transactions. Our solution employs an auction-based mechanism and blockchain oracles to address standardization challenges and enhance the accuracy of energy-related data. Additionally, an advanced identity management system ensures secure access to the trading system. Through smart contracts, energy producers and consumers engage directly in transparent and decentralized transactions. Despite challenges such as regulatory uncertainties and scalability concerns, our solution offers a promising alternative for building a more inclusive and sustainable energy future. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Classification Network Model Based on Hybrid Supervision for Industrial Surface Defect Detection

引用

International Journal of Pattern Recognition and Artificial Intelligence 2025年第5期39卷

作者： Qin, Runbing Chen, Ningjiang Gan, Shukun Guangxi University School of Computer Electronics and Information Nanning530004 China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Parallel Distributed and Intelligent Computing Guangxi University Nanning530004 China Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning530004 China

Industrial part surface defect detection aims to precisely locate defects in images, which is crucial for quality control in manufacturing. The traditional method needs to be designed in advance, but it has shortcomings in terms of generalization ability. Deep neural network-based defect detection faces issues such as low resolution, data scarcity, labeling costs, and high computation. Therefore, an improved solution is necessary to enhance industrial product quality control efficiency and accuracy. A new method is proposed that utilizes end-to-end training of a two-stage neural network based on segmentation with an extended training process. The gradient flow from the classification to the segmentation network is adjusted to prevent unstable features from interfering with learning. To address the problem of image oversampling and undersampling during training, a frequency sampling scheme for negative samples is introduced. Additionally, positive pixels in the region-based segmentation mask are weighted using the distance transform algorithm so that regions with a high probability of defects can be detected without detailed annotation. Experiments are conducted across three distinct defect datasets by applying hybrid supervision encompassing diverse conditions. In the optimal case, the AP rate of the proposed model on the DAGM and KolektorSDD datasets reaches 100%, and the AP rate on the Severstal Steel dataset reaches 98.99%. The experiments’ results show that the detection accuracy has improved greatly, showing how well the proposed method works in the industry. © 2025 World Scientific Publishing Company.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning to Design Transceiver for Integrated Sensing and Communications: A Satellite Communications Perspective

引用

IEEE Transactions on Wireless Communications 2025年

作者： Lukito, William D. Xiang, Wei Liu, Chang Lai, Phu Cheng, Peng Mao, Guoqiang La Trobe University School of Computing Engineering and Mathematical Sciences MelbourneVIC3086 Australia Southeast University Research Laboratory of Smart Driving and Intelligent Transportation Systems Jiangsu Nanjing211102 China

With its dual-functional advantages, integrated sensing and communications (ISAC) technologies can be further extended to satellite communications, enhancing global coverage services. However, achieving vast coverage would result in significant delays and considerable path losses. Motivated by this, in this paper, we focus on satellite-based ISAC (S-ISAC) systems and propose a general transceiver design framework incorporating both transmit waveform and receive filter. Unlike existing approaches, our approach uses a predictive joint transmit waveform and receive filter design that eliminates the need of channel estimation, thereby reducing time overhead. Additionally, a versatile weighting mechanism is designed to allow flexible prioritization between communications and sensing. To tackle the intractability of the ISAC transceiver design problem, we adopt a data-driven deep learning-based approach, where the model learns to design the transmit waveform and receive filter from historical channel data. Specifically, we propose a predictive optimization network (PONet), leveraging convolutional layers and a Transformer encoder to capture long-term spatial-temporal features and facilitate the learning capability. Numerical results demonstrate the effectiveness of the proposed PONet in terms of communications and sensing rates in S-ISAC networks in various system settings. © 2002-2012 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

AmgR: Algebraic Multigrid Accelerated on ReRAM 23

AmgR: Algebraic Multigrid Accelerated on ReRAM

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Mingjia Fan Xiaotian Tian Yintao He Junxian Li Yiru Duan Xiaozhe Hu Ying Wang Zhou Jin Weifeng Liu Super Scientific Software Laboratory China University of Petroleum-Beijing Institute of Computing Technology Chinese Academy of Sciences and SKLP Institute of Computing Technology CAS Tufts University USA Institute of Computing Technology Chinese Academy of Sciences and SKLP Institute of Computing Technology CAS and Research Center for Intelligent Computing Systems

ISBN: (纸本)9798350323481

Solving systems of linear equations is a fundamental problem in scientific computing, which has been extensively researched for decades. One of the most well-known solvers is Algebraic Multigrid (AMG), which is widely used in high performance computing due to its good scalability. But currently accelerating AMG relies on the traditional von Neumann architecture of storage and computation separation, which leads to a large data transmission overhead. In this work, we propose a ReRAM-based processing-in-memory (PIM) architecture named AmgR, which overcomes the limitations of the traditional von Neumann architecture for AMG ***, accelerating AMG on ReRAM is non-trivial, because (1) AMG has many computing kernels of various types; (2) there are irregular operations that cannot be directly performed using matrix-vector multiplication suitable for ReRAM, i.e., aggregation operation; (3) ReRAM has poor write endurance, and a lot of data during AMG acceleration needs to be rewritten into ReRAM, resulting in high write cost. To address these issues, firstly, we propose a flexible architecture, which can realize each kernel of AMG and is reused by many kernels to improve resource utilization. Secondly, we propose a dedicated unit to realize the aggregation operation. Finally, we present a new mapping strategy to greatly reduce the number of data handling and writes. The experimental results show that the performance of AmgR is improved by an average of one and two orders of magnitude compared to HYPRE on the CPU and AmgX on the GPU, respectively, while the energy consumption is reduced by an average of two and three orders of magnitude.

关键词： AMG

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：