检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zheng, Shenghe Wang, Hongzhi Liu, Xianglong Massive Data Computing Lab Harbin Institute of Technology China

Graph Neural Networks (GNNs) have shown great performance in various tasks, with the core idea of learning from data labels and aggregating messages within the neighborhood of nodes. However, the common challenges in graphs are twofold: insufficient accurate (high-quality) labels and limited neighbors for nodes, resulting in weak GNNs. Existing graph augmentation methods typically address only one of these challenges, often adding training costs or relying on oversimplified or knowledge-intensive strategies, limiting their generalization. To simultaneously address both challenges faced by graphs in a generalized way, we propose an elegant method called IntraMix. Considering the incompatibility of vanilla Mixup with the complex topology of graphs, IntraMix innovatively employs Mixup among inaccurate labeled data of the same class, generating high-quality labeled data at minimal cost. Additionally, it finds data with high confidence of being clustered into the same group as the generated data to serve as their neighbors, thereby enriching the neighborhoods of graphs. IntraMix efficiently tackles both issues faced by graphs and challenges the prior notion of the limited effectiveness of Mixup in node classification. IntraMix is a theoretically grounded plug-in-play method that can be readily applied to all GNNs. Extensive experiments demonstrate the effectiveness of IntraMix across various GNNs and datasets. Our code is available at: https://***/Zhengsh123/IntraMix. © 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

Duet: Efficient and Scalable Hybrid Neural Relation Understanding 40

Duet: Efficient and Scalable Hybrid Neural Relation Understa...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhang, Kaixin Wang, Hongzhi Lu, Yabin Li, Ziqi Shu, Chang Yan, Yu Yang, Donghua Harbin Institute of Technology Massive Data Computing Lab China

ISBN: (纸本)9798350317152

Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the work-load drift problem for a long time. Although both data-driven and hybrid methods are proposed to avoid this problem, most of them suffer from high training and estimation costs, limited scalability, instability, and long-tail distribution problems on high-dimensional tables, which seriously affects the practical application of learned cardinality estimators. In this paper, we prove that most of these problems are directly caused by the widely used progressive sampling. We solve this problem by introducing predicate information into the autoregressive model and propose Duet, a stable, efficient, and scalable hybrid method to estimate cardinality directly without sampling or any non-differentiable process, which can not only reduce the inference complexity from O(n) to O(1) compared to Naru and UAE but also achieve higher accuracy on high cardinality and high-dimensional tables. Experimental results show that Duet can achieve all the design goals above and be much more practical. Besides, Duet even has a lower inference cost on CPU than that of most learned methods on GPU. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

QCFE: An Efficient Feature Engineering for Query Cost Estimation 40

QCFE: An Efficient Feature Engineering for Query Cost Estima...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Yan, Yu Wang, Hongzhi Huang, Junfang Zhong, Dake Yu, Tao Zhang, Kaixin Yang, Man Wang, Tianqing Harbin Institute of Technology Massive Data Computing Lab China Huawei Open Gauss China

ISBN: (纸本)9798350317152

Query cost estimation is a classical task for database management. Recently, researchers have applied AI-driven methods to implement query cost estimation for achieving high accuracy. However, two defects of the feature design lead to poor time-accuracy efficiency in the query cost estimation task. On the one hand, existing works only encode the query plan and data statistics while ignoring some important variables, like storage structure, hardware, database knobs, etc. These variables also have a significant impact on the query cost. On the other hand, existing works suffer the heavy model training and model inference due to inefficient features, such as the index encoding of write-only workloads. To address the above two problems, we first propose an efficient feature engineering for query cost estimation, called QCFE, consisting of the feature snapshot and feature reduction algorithm. (1) We design a novel concept called feature snapshot to efficiently integrate the influences of the missing variables. (2) We propose a difference-propagation feature reduction method for query cost estimation to filter the ineffective features. Compared to state-of-the-art methods, QCFE demonstrates significant improvements in various aspects with well-known benchmarks. QCFE saves up to 50% time consumption for model training, resulting in more efficient and faster training processes. QCFE also optimizes the mean q-error by 19.8% in TPCH, leading to more precise query cost estimation. QCFE offers up to an impressive 8 times inference speedup in query inference throughput. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

IntraMix: intra-class mixup generation for accurate labels and neighbors 24

IntraMix: intra-class mixup generation for accurate labels a...

引用

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

作者： Shenghe Zheng Hongzhi Wang Xianglong Liu Massive Data Computing Lab Harbin Institute of Technology

ISBN: (纸本)9798331314385

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Scheduling Technology of computing Power Network Driven by Knowledge Graph

Automatic Scheduling Technology of Computing Power Network D...

引用

2022 CCF International Conference on Service Science, CCF ICSS 2022

作者： Bi, Yanheng Long, Yingchi Jin, Yanzheng Zheng, Shengwen Liu, Huaiyuan Wang, Hongzhi Harbin Institute of Technology Massive Data Computing Lab Harbin China

ISBN: (数字)9781665498616

ISBN: (纸本)9781665498616

In recent years, the demand for computing resources of AI industry is urgent because of the data explosion, which promoted the construction of computing power networks in the new era for operators. From the cloud network era to today's computing power network, stricter requirements are proposed to ensure the efficiency and security of computing services. Despite computing power scheduling technologies such as on-demand edge computing and efficient compute first network, knowledge graph techniques for graphs are less explored. As a new technology that can express the relationship between nodes in the graph extremely easily, knowledge graph has a natural advantage in expressing feature information of computing nodes in computing power network. Therefore, a novel knowledge graph representation for the architecture of computing power networks is proposed. And the knowledge graph of the computing power network is constructed by using the knowledge representation method. The scheduling tasks of computing power network is automatically executed by the proposed knowledge driven method based on the constructed knowledge graph. Different with the current scheduling technology of computing power network, the model will theoretically become more and more efficient and accurate with continuously addition of knowledge. © 2022 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Duet: Efficient and Scalable Hybrid Neural Relation Understanding

Duet: Efficient and Scalable Hybrid Neural Relation Understa...

引用

International Conference on data Engineering

作者： Kaixin Zhang Hongzhi Wang Yabin Lu Ziqi Li Chang Shu Yu Yan Donghua Yang Massive Data Computing Lab Harbin Institute of Technology

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the work-load drift problem for a long time. Although both data-driven and hybrid methods are proposed to avoid this problem, most of them suffer from high training and estimation costs, limited scalability, instability, and long-tail distribution problems on high-dimensional tables, which seriously affects the practical application of learned cardinality estimators. In this paper, we prove that most of these problems are directly caused by the widely used progressive sampling. We solve this problem by introducing predicate information into the autoregressive model and propose Duet, a stable, efficient, and scalable hybrid method to estimate cardinality directly without sampling or any non-differentiable process, which can not only reduce the inference complexity from $O(n)$ to $O(1)$ compared to Naru and UAE but also achieve higher accuracy on high cardinality and high-dimensional tables. Experimental results show that Duet can achieve all the design goals above and be much more practical. Besides, Duet even has a lower inference cost on CPU than that of most learned methods on GPU.

关键词： Training Costs Accuracy Scalability Estimation Graphics processing units data engineering

来源：评论

学校读者我要写书评

暂无评论

IntraMix: Intra-Class Mixup Generation for Accurate labels and Neighbors

arXiv

引用

arXiv 2024年

作者： Zheng, Shenghe Wang, Hongzhi Liu, Xianglong Massive Data Computing Lab Harbin Institute of Technology China

Graph Neural Networks (GNNs) have shown great performance in various tasks, with the core idea of learning from data labels and aggregating messages within the neighborhood of nodes. However, the common challenges in graphs are twofold: insufficient accurate (high-quality) labels and limited neighbors for nodes, resulting in weak GNNs. Existing graph augmentation methods typically address only one of these challenges, often adding training costs or relying on oversimplified or knowledge-intensive strategies, limiting their generalization. To simultaneously address both challenges faced by graphs in a generalized way, we propose an elegant method called IntraMix. Considering the incompatibility of vanilla Mixup with the complex topology of graphs, IntraMix innovatively employs Mixup among inaccurate labeled data of the same class, generating high-quality labeled data at minimal cost. Additionally, it finds data with high confidence of being clustered into the same group as the generated data to serve as their neighbors, thereby enriching the neighborhoods of graphs. IntraMix efficiently tackles both issues faced by graphs and challenges the prior notion of the limited effectiveness of Mixup in node classification. IntraMix is a theoretically grounded plug-in-play method that can be readily applied to all GNNs. Extensive experiments demonstrate the effectiveness of IntraMix across various GNNs and datasets. Our code is available at: https://***/Zhengsh123/IntraMix. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning

arXiv

引用

arXiv 2023年

作者： Zheng, Shenghe Wang, Hongzhi Mu, Tianyu Massive Data Computing Lab Harbin Institute of Technology China

Neural predictors have shown great potential in the evaluation process of neural architecture search (NAS). However, current predictor-based approaches overlook the fact that training a predictor necessitates a considerable number of trained neural networks as the labeled training set, which is costly to obtain. Therefore, the critical issue in utilizing predictors for NAS is to train a high-performance predictor using as few trained neural networks as possible. Although some methods attempt to address this problem through unsupervised learning, they often result in inaccurate predictions. We argue that the unsupervised tasks intended for the common graph data are too challenging for neural networks, causing unsupervised training to be susceptible to performance crashes in NAS. To address this issue, we propose a CurricuLum-guided Contrastive Learning framework for neural Predictor (DCLP). Our method simplifies the contrastive task by designing a novel curriculum to enhance the stability of unlabeled training data distribution during contrastive training. Specifically, we propose a scheduler that ranks the training data according to the contrastive difficulty of each data and then inputs them to the contrastive learner in order. This approach concentrates the training data distribution and makes contrastive training more efficient. By using our method, the contrastive learner incrementally learns feature representations via unsupervised data on a smooth learning curve, avoiding performance crashes that may occur with excessively variable training data distributions. We experimentally demonstrate that DCLP has high accuracy and efficiency compared with existing predictors, and shows promising potential to discover superior architectures in various search spaces when combined with search strategies. Our code is available at: https://***/Zhengsh123/DCLP. Copyright © 2023, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Duet: efficient and scalable hybriD neUral rElation undersTanding

arXiv

引用

arXiv 2023年

作者： Zhang, Kaixin Wang, Hongzhi Lu, Yabin Li, Ziqi Shu, Chang Yan, Yu Yang, Donghua Massive Data Computing Lab Harbin Institute of Technology China

Learned cardinality estimation methods have achieved high precision compared to traditional methods. Among learned methods, query-driven approaches have faced the workload drift problem for a long time. Although both data-driven and hybrid methods are proposed to avoid this problem, most of them suffer from high training and estimation costs, limited scalability, instability, and long-tail distribution problems on high-dimensional tables, which seriously affects the practical application of learned cardinality estimators. In this paper, we prove that most of these problems are directly caused by the widely used progressive sampling. We solve this problem by introducing predicate information into the autoregressive model and propose Duet, a stable, efficient, and scalable hybrid method to estimate cardinality directly without sampling or any nondifferentiable process, which can not only reduce the inference complexity from O(n) to O(1) compared to Naru and UAE but also achieve higher accuracy on high cardinality and highdimensional tables. Experimental results show that Duet can achieve all the design goals above and be much more practical. Besides, Duet even has a lower inference cost on CPU than that of most learned methods on GPU. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

QCFE: An Efficient Feature Engineering for Query Cost Estimation

QCFE: An Efficient Feature Engineering for Query Cost Estima...

引用

International Conference on data Engineering

作者： Yu Yan Hongzhi Wang Junfang Huang Dake Zhong Tao Yu Kaixin Zhang Man Yang Tianqing Wang Massive Data Computing lab Harbin Institute of Technology China Open Gauss Huawei China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

关键词： Training Costs Accuracy databases Estimation Throughput Hardware

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：