检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Yunfan Li, Changlun Luo, Yuyu Tang, Nan Thrust of Data Science and Analytics Information Hub The Hong Kong University of Science and Technology Guangzhou China

Missing value is a critical issue in data science, significantly impacting the reliability of analyses and predictions. Missing value imputation (MVI) is a longstanding problem because it highly relies on domain knowledge. Large language models (LLMs) have emerged as a promising tool for data cleaning, including MVI for tabular data, offering advanced capabilities for understanding and generating content. However, despite their promise, existing LLM techniques such as in-context learning and Chain-of-Thought (CoT) often fall short in guiding LLMs to perform complex reasoning for MVI, particularly when imputing derived missing values, which require mathematical formulas by considering data values across rows and columns. This gap underscores the need for further advancements in LLM methodologies to enhance their reasoning capabilities for derived missing values. To fill this gap, we propose SketchFill, a novel sketch-based method to guide LLMs in generating accurate formulas to impute missing numerical values. SketchFill first utilizes a general user-provided Meta-Sketch to generate a Domain-Sketch tailored to the context of the input dirty table. Subsequently, it fills this Domain-Sketch with formulas and outputs Python code, effectively bridging the gap between high-level abstractions and executable solutions. Additionally, SketchFill incorporates a Reflector component to verify the generated code. This Reflector assesses the accuracy and appropriateness of the outputs and iteratively refines the Domain-Sketch, ensuring that the imputation aligns closely with the underlying data patterns and relationships. Our experimental results demonstrate that SketchFill significantly outperforms state-of-the-art methods, achieving 56.2% higher accuracy than CoT-based methods and 78.8% higher accuracy than MetaGPT. This sets a new standard for automated data cleaning and advances the field of MVI for numerical values. Copyright © 2024, The Authors. All rights reserved.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

GraphWiz: An Instruction-Following Language Model for Graph Computational Problems

arXiv

引用

arXiv 2024年

作者： Chen, Nuo Li, Yuhan Tang, Jianheng Li, Jia Guangzhou China The Hong Kong University of Science and Technology Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China

Large language models (LLMs) have achieved impressive success across various domains, but their capability in understanding and resolving complex graph problems is less explored. To bridge this gap, we introduce GraphInstruct, a novel instruction-tuning dataset aimed at enabling language models to tackle a broad spectrum of graph problems through explicit reasoning paths. Utilizing GraphInstruct, we build GraphWiz, an open-source language model capable of solving various graph computational problems while generating clear reasoning processes. To further enhance the model’s performance and reliability, we integrate the Direct Preference Optimization (DPO) framework within the graph problem-solving context. The improved model, GraphWiz-DPO, achieves an average accuracy of 65% across nine tasks with different complexity levels, surpassing GPT-4 which has an average accuracy of 43.8%. Our study also investigates the relationship between training data volume and model performance, emphasizing the risk of overfitting as data volume increases. Additionally, we explore the transferability of the proposed model across different tasks and datasets, demonstrating its robust zero-shot generalization capability. GraphWiz offers a new blueprint and valuable insights for developing LLMs specialized in graph reasoning and problem-solving. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Optimal clustering with bandit feedback

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 8799-8852页

作者： Junwen Yang Zixin Zhong Vincent Y. F. Tan Institute of Operations Research and Analytics National University of Singapore Singapore Thrust of Data Science and Analytics Hong Kong University of Science and Technology (Guangzhou) Guangzhou Guangdong China Department of Mathematics Department of Electrical and Computer Engineering Institute of Operations Research and Analytics National University of Singapore Singapore

This paper considers the problem of online clustering with bandit feedback. A set of arms (or items) can be partitioned into various groups that are unknown. Within each group, the observations associated to each of the arms follow the same distribution with the same mean vector. At each time step, the agent queries or pulls an arm and obtains an independent observation from the distribution it is associated to. Subsequent pulls depend on previous ones as well as the previously obtained samples. The agent's task is to uncover the underlying partition of the arms with the least number of arm pulls and with a probability of error not exceeding a prescribed constant δ. The problem proposed finds numerous applications from clustering of variants of viruses to online market segmentation. We present an instance-dependent information-theoretic lower bound on the expected sample complexity for this task, and design a computationally efficient and asymptotically optimal algorithm, namely Bandit Online Clustering (BOC). The algorithm includes a novel stopping rule for adaptive sequential testing that circumvents the need to exactly solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower bound asymptotically, and significantly outperforms a non-adaptive baseline algorithm.

关键词： clustering K-means online learning multi-armed bandits pure exploration

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Graph Learning for Drug-Drug Interaction Prediction

arXiv

引用

arXiv 2024年

作者： Shen, Zhenqian Zhou, Mingyang Zhang, Yongqi Yao, Quanming Department of Electronic Engineering Tsinghua University Beijing China Thrust of Data Science and Analytics The Hong Kong University of Science and Technology Guangzhou China

Predicting drug-drug interaction (DDI) plays an important role in pharmacology and healthcare for identifying potential adverse interactions and beneficial combination therapies between drug pairs. Recently, a flurry of graph learning methods have been introduced to predict drug-drug interactions. However, evaluating existing methods has several limitations, such as the absence of a unified comparison framework for DDI prediction methods, lack of assessments in meaningful real-world scenarios, and insufficient exploration of side information usage. In order to address these unresolved limitations in the literature, we propose a DDI prediction benchmark on graph learning. We first conduct unified evaluation comparison among existing methods. To meet realistic scenarios, we further evaluate the performance of different methods in settings with new drugs involved and examine the performance across different DDI types. Component analysis is conducted on the biomedical network to better utilize side information. Through this work, we hope to provide more insights for the problem of DDI prediction. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models

arXiv

引用

arXiv 2025年

作者： Peng, Zengqi Wang, Yubin Han, Xu Zheng, Lei Ma, Jun Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?

arXiv

引用

arXiv 2023年

作者： Zhang, Haohan Hua, Fengrui Xu, Chengjin Kong, Hao Zuo, Ruiting Guo, Jian Artificial Intelligence Thrust The Hong Kong University of Science and Technology Guangzhou China Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Financial Technology Thrust The Hong Kong University of Science and Technology Guangzhou China

The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies. LLMs excel in analyzing sentiments about listed companies from financial news, providing critical insights for trading decisions. However, the performance of LLMs in this task varies substantially due to their inherent characteristics. This paper introduces a standardized experimental procedure for comprehensive evaluations. We detail the methodology using three distinct LLMs, each embodying a unique approach to performance enhancement, applied specifically to the task of sentiment factor extraction from large volumes of Chinese news summaries. Subsequently, we develop quantitative trading strategies using these sentiment factors and conduct back-tests in realistic scenarios. Our results will offer perspectives about the performances of Large Language Models applied to extracting sentiments from Chinese news texts. © 2023, CC BY.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

VRFfall: Cross Vision-RF Fall Detection with Camera and mmWave Radar

VRFfall: Cross Vision-RF Fall Detection with Camera and mmWa...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yanying Zhu Haotian Song Kaishun Wu Min Sun Li Zhou Thrust of Data Science and Analytics The Hong Kong University of Science and Technology(Guangzhou) Guangzhou China Thrust of Internet of Things The Hong Kong University of Science and Technology(Guangzhou) Guangzhou China China Mobile Information Technology Shenzhen China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Accurate fall detection systems are vital to address the global health concern of elderly falls, which often lead to severe injuries, hospitalizations, and fatalities. Since falls can happen at any time in any location, it is imperative to have a comprehensive system that boasts high applicability across a broad range of scenarios, operating seamlessly 24/7. However, within a range of fall detection systems, most of the existing work is built upon mono-modal sensors, which are inevitably inherited and constrained by mono-modal shortages. To overcome the constraints of mono-modal systems, we introduce VRFfall, a novel multi-modal fall detection system that seamlessly fuses mmWave radar and camera technologies. As a system with high generalization capabilities, VRFfall supports both multi-modal and mono-modal inputs with its independent feature extraction pipeline for each modality. Utilizing a cross-modal knowledge transfer design, VRFfall enhances performance with mono-modal input by leveraging fused knowledge from the other modality. Moreover, to ensure optimal fusion decisions under modal discrepancies, VRFfall incorporates an adaptive Modal Quality Assessment Module (MQAM) that dynamically evaluates and fuses features from both modalities. Extensive evaluations using a dataset collected from 20 volunteers across two environments and three conditions have been conducted on VRFfall. The results demonstrate its high performance and excellent generalization across diverse environments and conditions, promising a 24/7 continuous fall detection system.

关键词： Fuses Radar detection Radar Cameras Sensor systems Sensors Quality assessment Fall detection Millimeter wave communication Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Incentive Mechanism Design for Federated Learning With Dynamic Network Pricing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ding, Ningning Gao, Lin Huang, Jianwei Data Science and Analytics Thrust Internet of Things Thrust Information Hub Guangzhou China Harbin Institute of Technology School of Electronics and Information Engineering Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Shenzhen China The Chinese University of Hong Kong School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen Shenzhen518172 China

Federated learning protects users' data privacy by sharing users' local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users' contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users' private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under three interaction structures of the participants. We show that the coordinated structure is better than the two uncoordinated structures, as it avoids the selfish behaviors of the network operator and the server;the vertically uncoordinated structure is better than the horizontally uncoordinated structure, as it avoids the interests misalignment between the server and the network operator. We also propose multi-period network pricing to reduce the implementation complexity of dynamic pricing. Numerical results based on real-world datasets show that our proposed mechanisms decrease the server's cost by up to 24.87% and increase the network operator's profit by up to 1245.25%, compared with the state-of-the-art benchmarks. © 2025 IEEE. 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

Dionysus: Recovering Scene Structures by Dividing into Semantic Pieces

Dionysus: Recovering Scene Structures by Dividing into Seman...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Likang Wang Lei Chen Department of Computer Science and Engineering The Hong Kong University of Science and Technology Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou)

Most existing 3D reconstruction methods result in either detail loss or unsatisfying efficiency. However, effectiveness and efficiency are equally crucial in real-world applications, e.g., autonomous driving and augmented reality. We argue that this dilemma comes from wasted resources on valueless depth samples. This paper tackles the problem by proposing a novel learning-based 3D reconstruction framework named Dionysus. Our main contribution is to find out the most promising depth candidates from estimated semantic maps. This strategy simultaneously enables high effectiveness and efficiency by attending to the most reliable nominators. Specifically, we distinguish unreliable depth candidates by checking the cross-view semantic consistency and allow adaptive sampling by redistributing depth nominators among pixels. Experiments on the most popular datasets confirm our proposed framework's effectiveness.

关键词：

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：