检索结果-内蒙古大学图书馆

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

作者： Duo Wang Yuan Zuo Fengzhi Li Junjie Wu MIIT Key Laboratory of Data Intelligence and Management Beihang University

ISBN: (纸本)9798331314385

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN's representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method's effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors. Our code is available at https://***/W-rudder/TEA-GLM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Core Technological Topics in the New Energy Vehicle Industry: The SAO-BERTopic Topic Modeling Approach Based on Patent Text Mining 5

Identification of Core Technological Topics in the New Energ...

引用

Joint Workshop of the 5th Extraction and Evaluation of Knowledge Entities from Scientific Documents and the 4th AI + Informetrics, EEKE-AII 2024

作者： Zhu, Jianxin Chuang, Yutong Wang, Zhinan Li, Yunke Harbin Engineering University School of Economics and Management 150001 China Key Laboratory of Big Data and Business Intelligence Technology Ministry of Industry and Information Technology China

In the new energy vehicle industry, precise identification of core technologies is the key to promoting innovation and maintaining market competitiveness. In this article, a comprehensive approach combining information weight method and SAO-BERTopic topic model is proposed to extract and analyze core technologies from large-scale patent data. Through in-depth analysis of Incopat patent database, we use the information weight method to select high-quality core patents from four dimensions: technological, strategic, law and market value. These selected patents form the basis of the research data, which is then applied to the SAO-BERTopic model, which combines the advanced semantic understanding capabilities of BERTopic with the fine-structured characteristics of SAO analysis, greatly improving the efficiency and accuracy of identifying complex technical topics. This innovation of this research is not only applicable to the analysis of the technological development of the new energy vehicle industry, but also can provide valuable reference for other high-tech industries such as biomedicine, renewable energy and information technology. These fields also need to identify core technologies from a large number of patents. SAO-BERTopic's structured analysis framework can help these industries to insight into technology development trends, identify innovation opportunities, and provide data-driven decision support for enterprises, research institutions and governments, thus playing an important role in technology planning and market commercialization. © Copyright 2024 for this paper by its authors.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

BASES: Large-scale Web Search User Simulation with Large Language Model based Agents

BASES: Large-scale Web Search User Simulation with Large Lan...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Ren, Ruiyang Qiu, Peng Qu, Yingqi Liu, Jing Zhao, Wayne Xin Wu, Hua Wen, Ji-Rong Wang, Haifeng Gaoling School of Artificial Intelligence Renmin University of China China Baidu Inc. China Beijing Key Laboratory of Big Data Management and Analysis Methods China

ISBN: (纸本)9798891761681

Due to the excellent capacities of large language models (LLMs), it becomes feasible to develop LLM-based agents for reliable user simulation. Considering the scarcity and limit (e.g., privacy issues) of real user data, in this paper, we conduct large-scale user simulations for the web search scenario to improve the analysis and modeling of user search behavior. Specially, we propose BASES, a novel user simulation framework with LLM-based agents, designed to facilitate comprehensive simulations of web search user behaviors. Our simulation framework can generate unique user profiles at scale, which subsequently leads to diverse search behaviors. To demonstrate the effectiveness of BASES, we conduct evaluation experiments based on two human benchmarks in both Chinese and English, demonstrating that BASES can effectively simulate large-scale human-like search behaviors. To further accommodate the research on web search, we develop WARRIORS, a new large-scale dataset encompassing web search user behaviors, including both Chinese and English versions, which can greatly bolster research in the field of information retrieval. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Understanding Human Preferences: Towards More Personalized Video to Text Generation 24

Understanding Human Preferences: Towards More Personalized V...

引用

33rd ACM Web Conference, WWW 2024

作者： Wu, Yihan Song, Ruihua Chen, Xu Jiang, Hao Cao, Zhao Yu, Jin Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Poisson Lab Beijing China

ISBN: (纸本)9798400701719

While previous video to text models have achieved remarkable successes, they mostly focus on how to understand the video contents in a general sense, but fail to capture the human personalized preferences, which is highly demanded for an engaging multimodal chatbots. Different from user modeling in collaborative filtering, there is no other user behaviors in inference as a real-time video stream is coming. In this paper, we formally define the task of personalized video commenting task and design an end-to-end personalized framework for solving this task. In specific, we argue that the personalization for video comment generation can be reflected in two aspects, that is, (1) for the same video, different users may comment on different clips, and (2) for the same clip, different people may also express various opinions with diverse commentary styles. Motivated by these considerations, we design our framework based on two components. The first one is a clip selector, which is responsible for predicting the clips that the user may comment in the video. The second one is a text generator, which aims to produce the comment based on the above predicted clips and the user's preference. In our framework, these two components are optimized in an end-to-end manner to mutually enhance each other, where we design confidence-aware scheduled sampling and iterative inference strategies to solve the problem that the ground truth clips are absent in the inference phase. As the absence of personalized video to text dataset, we collect and release a new dataset for studying this problem. We conduct extensive experiments to demonstrate the effectiveness of our model. © 2024 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Federated intelligence for Intelligent Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-5页

作者： Zhang, Weishan Zhang, Baoyu Jia, Xiaofeng Qi, Hongwei Qin, Rui Li, Juanjuan Tian, Yonglin Liang, Xiaolong Wang, Fei-Yue School of China University of Petroleum Qingdao China Department of Data Management Big Data Centre Beijing Beijing China Technology Company Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Innovation Engineering Macau University of Science and Technology Macao China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

This letter is a brief summary of a series of IEEE TIV's decentralized and hybrid workshops (DHWs) on Federated intelligence for Intelligent Vehicles. The discussed results are: 1) Different scales of large models (LMs) can be federated and deployed on IVs, and three types of federated collaboration between large and small models can be adopted for IVs. 2) Federated fine-tuning of LMs is beneficial for IVs data security. 3) The sustainability of IVs can be improved through optimizing existing models and continuous learning using federated intelligence. 4) LM-enhanced knowledge can make IVs smarter. IEEE

关键词： Intelligent vehicle highway systems

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Particle Swarm Optimization Algorithm Based on Decomposition and Multi-Selection Strategy

引用

Computers, Materials & Continua 2025年第1期82卷 997-1026页

作者： Li Ma Cai Dai Xingsi Xue Cheng Peng School of Computer Science Shaanxi Normal UniversityXi’an710119China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Information Construction and Management Center and Institute of Artificial Intelligence and Educational New Productivity Ningxia Normal UniversityGuyuan756099China

The multi-objective particle swarm optimization algorithm(MOPSO)is widely used to solve multi-objective optimization *** the article,amulti-objective particle swarm optimization algorithmbased on decomposition and multi-selection strategy is proposed to improve the search ***,two update strategies based on decomposition are used to update the evolving population and external archive,***,a multiselection strategy is *** first strategy is for the subspace without a non-dominated *** the neighbor particles,the particle with the smallest penalty-based boundary intersection value is selected as the global optimal solution and the particle far away fromthe search particle and the global optimal solution is selected as the personal optimal solution to enhance global *** second strategy is for the subspace with a non-dominated *** the neighbor particles,two particles are randomly selected,one as the global optimal solution and the other as the personal optimal solution,to enhance local *** third strategy is for Pareto optimal front(PF)discontinuity,which is identified by the cumulative number of iterations of the subspace without non-dominated *** the subsequent iteration,a new probability distribution is used to select from the remaining subspaces to ***,an adaptive inertia weight update strategy based on the dominated degree is designed to further improve the search ***,the proposed algorithmis compared with fivemulti-objective particle swarm optimization algorithms and five multi-objective evolutionary algorithms on 22 test *** results show that the proposed algorithm has better performance.

关键词： Multi-objective optimization multi-objective particle swarm optimization decomposition multi-selection strategy

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training 41

Unlocking the Power of Spatial and Temporal Information in M...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Jinxia Su, Bing Zhao, Wayne Xin Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Information Renmin University of China China

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in off-the-shelf multi-modal medical datasets, most existing methods have not thoroughly tapped into such extensive supervision signals. In this paper, we introduce the Med-ST framework for fine-grained spatial and temporal modeling to exploit information from multiple spatial views of chest radiographs and temporal historical records. For spatial modeling, Med-ST employs the Mixture of View Expert (MoVE) architecture to integrate different visual features from both frontal and lateral views. To achieve a more comprehensive alignment, Med-ST not only establishes the global alignment between whole images and texts but also introduces modality-weighted local alignment between text tokens and spatial regions of images. For temporal modeling, we propose a novel cross-modal bidirectional cycle consistency objective by forward mapping classification (FMC) and reverse mapping regression (RMR). By perceiving temporal information from simple to complex, Med-ST can learn temporal semantics. Experimental results across four distinct tasks demonstrate the effectiveness of Med-ST, especially in temporal classification tasks. Our code and model are available at https://***/SVT-Yang/MedST. Copyright 2024 by the author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

arXiv

引用

arXiv 2024年

作者： Wang, Duo Zuo, Yuan Li, Fengzhi Wu, Junjie MIIT Key Laboratory of Data Intelligence and Management Beihang University China

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN’s representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method’s effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors. Our code is available at https://***/W-rudder/TEA-GLM. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? 38

Are High-Degree Representations Really Unnecessary in Equiva...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Cen, Jiacheng Li, Anyi Lin, Ning Ren, Yuxiang Wang, Zihe Huang, Wenbing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China 2012 Laboratories Huawei Technologies Shanghai China

Equivariant Graph Neural Networks (GNNs) that incorporate the E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models, EGNN [1] leverages a simple scalarization technique to perform equivariant message passing over only Cartesian vectors (i.e., 1st-degree steerable vectors), enjoying greater efficiency and efficacy compared to equivariant GNNs using higher-degree steerable vectors. This success suggests that higher-degree representations might be unnecessary. In this paper, we disprove this hypothesis by exploring the expressivity of equivariant GNNs on symmetric structures, including k-fold rotations and regular polyhedra. We theoretically demonstrate that equivariant GNNs will always degenerate to a zero function if the degree of the output representations is fixed to 1 or other specific values. Based on this theoretical insight, we propose HEGNN, a high-degree version of EGNN to increase the expressivity by incorporating high-degree steerable vectors while still maintaining EGNN's advantage through the scalarization trick. Our extensive experiments demonstrate that HEGNN not only aligns with our theoretical analyses on a toy dataset consisting of symmetric structures, but also shows substantial improvements on other complicated datasets without obvious symmetry, including N-body and MD17. Our study potentially showcase an effective way of modeling high-degree representations in equivariant GNNs. © 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

Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing

Uniform Attention Maps: Boosting Image Fidelity in Reconstru...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Mo, Wenyi Zhang, Tianyu Bai, Yalong Su, Bing Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Du Xiaoman Technology China

ISBN: (纸本)9798331510831

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering simplicity and efficiency. However, existing tuning-free approaches often struggle with balancing fidelity and editing precision. Reconstruction errors in DDIM Inversion are partly attributed to the cross-attention mechanism in U-Net, which introduces misalignments during the inversion and reconstruction process. To address this, we analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps, significantly enhancing image reconstruction fidelity. Our method effectively minimizes distortions caused by varying text conditions during noise prediction. To complement this improvement, we introduce an adaptive mask-guided editing technique that integrates seamlessly with our reconstruction approach, ensuring consistency and accuracy in editing tasks. Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios. This study underscores the potential of uniform attention maps to enhance the fidelity and versatility of diffusion-based image processing methods. Code is available at https://***/Mowenyii/Uniform-Attention-Maps. © 2025 IEEE.

关键词： Photointerpretation

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：