检索结果-内蒙古大学图书馆

ChemDFM-X: towards large multimodal model for chemistry

science China(Information sciences) 2024年第12期67卷 99-100页

作者： Zihan ZHAO Bo CHEN Jingpiao LI Lu CHEN Liyang WEN Pengyu WANG Zichen ZHU Danyang ZHANG Yansi LI Zhongyang DAI Xin CHEN Kai YU X-LANCE Lab Department of Computer Science and EngineeringMoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Suzhou Laboratory

Chemistry, as a naturally multimodal discipline, plays a crucial role in various vital fields such as pharmaceutical research and material manufacturing. Therefore, research on artificial intelligence(AI) for chemistry has garnered increasing attention. Despite the rapid development, most of the chemical AI models today mainly focus on single tasks with unimodal input [1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis 41

UP2ME: Univariate Pre-training to Multivariate Fine-tuning a...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yunhao Liu, Minghao Zhou, Shengyang Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China

Despite the success of self-supervised pre-training in texts and images, applying it to multivariate time series (MTS) falls behind tailored methods for tasks like forecasting, imputation and anomaly *** propose a general-purpose framework, named UP2ME (Univariate Pre-training to Multivariate Fine-tuning).It conducts task-agnostic pre-training when downstream tasks are *** the task and setting (*** length) are determined, it gives sensible solutions with frozen pre-trained parameters, which has not been achieved ***2ME is further refined by fine-tuning.A univariate-to-multivariate paradigm is devised to address the heterogeneity of temporal and cross-channel *** univariate pre-training, univariate instances with diverse lengths are generated for Masked AutoEncoder (MAE) pre-training, discarding cross-channel *** pretrained model handles downstream tasks by formulating them into specific mask-reconstruction *** multivariate fine-tuning, it constructs a dependency graph among channels using the pre-trained encoder to enhance cross-channel dependency *** on eight real-world datasets show its SOTA performance in forecasting and imputation, approaching task-specific performance in anomaly *** code is available at https://***/Thinklab-SJTU/UP2ME. Copyright 2024 by the author(s)

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

DITune: A Reinforcement Learning Based Framework for Automated Database Index Selection 18

DITune: A Reinforcement Learning Based Framework for Automat...

引用

18th International Conference on Ubiquitous Information Management and Communication, IMCOM 2024

作者： Huang, Xiuqi Gao, Xiaofeng Chen, Guihai Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350331011

Index selection is a crucial and essential aspect of database management systems (DBMS) aiming to optimize performance, and it is also one of the most time-consuming and laborious tasks for database administrators (DBAs). Therefore, automatic methods and tools are urgently needed to help DBAs choose a good index configuration for workloads. We propose a recommender system named DITune (Database Index Tuning) which can automatically analyze workloads, explore the potential benefits of indexes, and adjust the index configuration. We first implement a rule-based method to embed the database workload and data distribution feature. Then we utilize the Deep Deterministic Policy Gradient (DDPG) algorithm to generate index recommendations and construct index configuration. Moreover, we design a benchmark based on the standard TPC-C to validate the performance of our method under the varying workload patterns, query complexity, and running phase length. The experiment results show the effectiveness and robustness of DITune and indicate that the data-driven prediction outperforms those models based on cost estimation. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

RL with Balanced Reward and Masking Mechanism for Multi-NUMA Virtual Machine Scheduling 19

RL with Balanced Reward and Masking Mechanism for Multi-NUMA...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Gao, Yucen Cheng, Yunlong Ping, Chan Tin Gao, Xiaofeng Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798331507817

With the rapid development of data center and cloud computing, the importance of resource management is increasing in recent years. In this paper, we focus on the virtual machine scheduling problem in resource management, that is, how to allocate the limited virtual machine resources when a request arrives. Existing works usually model the virtual machine scheduling problem as a bin-packing problem, but they do not consider the multi-NUMA architecture servers that have been widely used in recent years. Compared with the traditional symmetric multiprocessing architecture, the multi-NUMA architecture has the advantages of faster access time and higher energy efficiency, which is more suitable for dealing with today’s scenarios with a large number of computing requirements. In this paper, we first formalize the multi-NUMA virtual machine scheduling problem as a combinatorial optimization problem and explain why it is suitable to be solved by reinforcement learning. A reinforcement learning model called BM-DQN is then proposed, which designs a balanced reward function suitable for the multi-NUMA architecture and adopts a masking mechanism to screen out the optional servers in each step of reinforcement learning, so as to improve the solution performance. Experimental results on the open-source real-world virtual machine scheduling dataset of Huawei Cloud show that BM-DQN is superior to the existing methods in terms of the number of completed requests. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Natural Image Matting with Attended Global Context

引用

Journal of computer science & Technology 2023年第3期38卷 659-673页

作者：张億一牛力 Yasushi Makihara 张健夫赵维杰 Yasushi Yagi 张丽清 MoE Key Lab of Artificial Intelligence Department of Computer Science and EngineeringShanghai Jiao Tong University Shanghai 200240China Department of Intelligent Media Institute of Scientific and Industrial ResearchOsaka UniversityOsaka 565-0871Japan

Image matting is to estimate the opacity of foreground objects from an image. A few deep learning based methods have been proposed for image matting and perform well in capturing spatially close information. However, these methods fail to capture global contextual information, which has been proved essential in improving matting performance. This is because a matting image may be up to several megapixels, which is too big for a learning-based network to capture global contextual information due to the limit size of a receptive field. Although uniformly downsampling the matting image can alleviate this problem, it may result in the degradation of matting performance. To solve this problem, we introduce a natural image matting with the attended global context method to extract global contextual information from the whole image, and to condense them into a suitable size for learning-based network. Specifically, we first leverage a deformable sampling layer to obtain condensed foreground and background attended images respectively. Then, we utilize a contextual attention layer to extract information related to unknown regions from condensed foreground and background images generated by a deformable sampling layer. Besides, our network predicts a background as well as the alpha matte to obtain more purified foreground, which contributes to better qualitative performance in composition. Comprehensive experiments show that our method achieves competitive performance on both Composition-1k and the *** benchmark quantitatively and qualitatively.

关键词： image matting global context deformable sampling

来源：评论

学校读者我要写书评

暂无评论

Corruption Robust Dynamic Pricing in Liner Shipping under Capacity Constraint 40

Corruption Robust Dynamic Pricing in Liner Shipping under Ca...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Hu, Yongyi Lit, Xueyan Wei, Xikai Shi, Yangguang Gao, Xiaofeng Chen, Guihai Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering China School of Computer Science and Technology Shandong University China

ISBN: (纸本)9798350317152

The shipping industry has irreplaceable importance in international trade and commerce. How to dynamically price different containers has long been a hot topic due to its direct connection to the final revenue. Two critical observations have been made after a comprehensive survey within a top liner company, China Ocean Shipping Company (COSCO). (1) Each type of container carried on a liner ship has its maximum capacity. (2) The sales volume is occasionally subject to huge fluctuations due to rare uncontrollable factors, such as COVID. Based on the above two points and the liner routine's periodic nature, we model the dynamic pricing problem as an episodic MDP model integrating with both capacity constraints and adversarial corruption, named C3-MDP. To maximize the cumulative revenue in the C3-MDP setting, we propose a programming framework, Bonus-Exploration based Episodic Programming (BEEP). This framework can directly accommodate the linear programming algorithm to form the algorithm BEEP-LP, which provides the episode-wise greedy optimal strategy. Furthermore, a detailed regret analysis is provided, showing that BEEP-LP has a regret that is sublinear in the number of episodes. Combining deep techniques, we also present an approximation algorithm BEEP-DQN in the case of large state-action space to strike a balance between the running time and the performance. Abundant experiments based on real container sales data exhibit the rationality of C3-MDP and the effectiveness of BEEP. © 2024 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

ELA: A Time-Series Forecasting Model for Liner Shipping Based on EMD-LSTM and Attention 11th

ELA: A Time-Series Forecasting Model for Liner Shipping Bas...

引用

11th International Conference on Computational Data and Social Networks, CSoNet 2022

作者： Chen, Jiadong Gao, Xiaofeng Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031263026

The development of modern information technology has led to the digital and intelligent transformation of many traditional industries. In order to face the challenge of difficult transition, liner shipping industry is in urgent need of prediction methods for strategy adjustment, and much research remains to be done in this area. In our paper, we put forward a time-series forecasting model named ELA based on modified EMD-LSTM (Empirical Mode Decomposition and Long Short-Term Memory), AR (Autoregressive) and the attention mechanism. Tailored for handling the market characteristics of the liner shipping industry, our method effectively reduces the negative impact of noise on model training and learns the short-term dependencies and long-term trend in time series. Experiments on real-world liner shipping datasets show the powerful prediction performance of ELA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Data-Driven Imputation Model for Incomplete Event Series 9th

An Adaptive Data-Driven Imputation Model for Incomplete Eve...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Chen, Jiadong Ye, Hengyu Gao, Xiaofeng Wu, Fan Kong, Linghe Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031466601

Event sequences play as a general fine-grained representation for temporal asynchronous event streams. However, in practice, event sequences are often fragmentary and incomplete with censored intervals or missing data, making it hard for downstream prediction and decision-making tasks. In this work, we propose a fresh extension on the definition of the temporal point process, which conventionally characterizes chronological prediction based on historical events, and introduce inverse point process that characterizes counter-chronological attribution based on future events. These two point process models allow us to impute missing events for one partially observed sequence with conditional intensities in two symmetric directions. We further design a peer imitation learning algorithm that lets two models cooperatively learn from each other, leveraging imputed sequences given by the counterpart as the supervised signal. The training process consists of iterative learning of two models and facilitates them to achieve a consensus. We conduct extensive experiments on both synthetic and real-world datasets, which demonstrate that our model can recover incomplete event sequences very close to the ground-truth, with averagely 49.40% improvement compared with related competitors measured by normalized optimal transport distance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Learning Divergence Fields for Shift-Robust Graph Representations 41

Learning Divergence Fields for Shift-Robust Graph Representa...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wu, Qitian Nie, Fan Yang, Chenxiao Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China

Real-world data generation often involves certain geometries (e.g., graphs) that induce instance-level interdependence. This characteristic makes the generalization of learning models more difficult due to the intricate interdependent patterns that impact data-generative distributions and can vary from training to testing. In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging generalization problem with interdependent data. We generalize the diffusion equation with stochastic diffusivity at each time step, which aims to capture the multi-faceted information flows among interdependent data. Furthermore, we derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains. Regarding practical implementation, we introduce three model instantiations that can be considered as the generalized versions of GCN, GAT, and Transformers, respectively, which possess advanced robustness against distribution shifts. We demonstrate their promising efficacy for out-of-distribution generalization on diverse real-world datasets. Source codes are available at https://***/fannie1208/GLIND. Copyright 2024 by the author(s)

关键词： Stochastic systems

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：