检索结果-内蒙古大学图书馆

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhang, Wentao Wang, Yexin You, Zhenbang Li, Yang Cao, Gang Yang, Zhi Cui, Bin Center for Machine Learning Research Peking University China Key Lab of High Confidence Software Technologies Peking University China Institute of Advanced Algorithms Research Shanghai China Institute of Computational Social Science Peking University Qingdao China National Engineering Labratory for Big Data Analytics and Applications China TEG Tencent Inc. Department of Data Platform China Beijing Academy of Artificial Intelligence China

ISBN: (纸本)9798350317152

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Temporal Knowledge Graph Reasoning via Time-Distributed Representation Learning

Temporal Knowledge Graph Reasoning via Time-Distributed Repr...

引用

IEEE International Conference on data Mining (ICDM)

作者： Kangzheng Liu Feng Zhao Guandong Xu Xianzhi Wang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Data Science and Machine Intelligence Lab University of Technology Sydney Sydney Australia

Temporal knowledge graph (TKG) reasoning has attracted significant attention. Recent approaches for modeling historical information have led to great advances. However, the problems of time variability and unseen entities have become two major obstacles preventing further development. The time variability problem means that different historical timestamps play different roles in the inference process. Furthermore, in the context of time variability, the unseen entity problem means that a query cannot obtain a predicted entity that is unseen in the scale-varying history rather than in a fixed set, thus turning from static to dynamic. In this paper, we propose a novel method named DHU-NET for addressing the time variability challenge and the dynamic unseen entity challenge derived from it. With regard to the former concern, we propose a time-distributed representation learning method based on a graph convolutional network(GCN) and a self-attention mechanism, which learns the distributed representations of facts at different historical timestamps and comprehensively pays different levels of attention to the different timestamps. With regard to the latter issue, we extract the unseen entities from a global static KG based on a copy mechanism and bring them into consideration during the final prediction step. Experiments on six benchmark datasets demonstrate the substantial improvements achieved by DHUNET in terms of multiple evaluation metrics. Our released codes are available at https://***/CGCL-codes/DHUNET.

关键词： Representation learning Measurement Knowledge engineering Predictive models Turning Cognition data models

来源：评论

学校读者我要写书评

暂无评论

RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation

RETIA: Relation-Entity Twin-Interact Aggregation for Tempora...

引用

International Conference on data Engineering

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://***/CGCL-codes/RETIA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating fish weight growth in aquaponic farming through machine learning techniques

Estimating fish weight growth in aquaponic farming through m...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Purushottam Kumar Pranav Tiwari U Srinivasulu Reddy CoE in Artificial Intelligence Machine Learning & Data Analytics Lab National Institute of Technology Trichy India Computer Science and Engineering Indian Institute of Information Technology Tiruchirappalli Trichy India Department of Computer Applications Machine Learning & Data Analytics Lab National Institute of Technology Trichy India

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won’t be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessment of Robust Multi-objective Evolutionary Algorithms on Robust and Noisy Environments 12th

Assessment of Robust Multi-objective Evolutionary Algorithms...

引用

12th Brazilian Conference on Intelligent Systems, BRACIS 2023

作者： de Sousa, Mateus Clemente Meneghini, Ivan Reinaldo Guimarães, Frederico Gadelha Instituto Federal de Minas Gerais Minas Gerais Bambuí Brazil Instituto Federal de Minas Gerais Minas Gerais Ibirité Brazil Universidade Federal de Minas Gerais Minas Gerais Belo Horizonte Brazil Machine Intelligence and Data Science – MINDS Lab Universidade Federal de Minas Gerais Belo Horizonte Brazil

ISBN: (纸本)9783031453915

Robust optimization considers uncertainty in the decision variables while noisy optimization concerns with uncertainty in the evaluation of objective and constraint functions. Although many evolutionary algorithms have been proposed to deal with robust or noisy optimization problems, the research question approached here is whether these methods can deal with both types of uncertainties at the same time. In order to answer this question, we extend a test function generator available in the literature for multi-objective optimization to incorporate uncertainties in the decision variables and in the objective functions. It allows the creation of scalable and customizable problems for any number of objectives. Three evolutionary algorithms specifically designed for robust or noisy optimization were selected: RNSGA-II and RMOEA/D, which utilize Monte Carlo sampling, and the C-RMOEA/D, which is a coevolutionary MOEA/D that uses a deterministic robustness measure. We did experiments with these algorithms on multi-objective problems with (i) uncertainty in the decision variables, (ii) noise in the output, and (iii) with both robust and noisy problems. The results show that these algorithms are not able to deal with simultaneous uncertainties (noise and perturbation). Therefore, there is a need for designing algorithms to deal with simultaneously robust and noisy environments. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Adversarial attribute-image person re-identification

arXiv

引用

arXiv 2017年

作者： Yin, Zhou Zheng, Wei-Shi Wu, Ancong Yu, Hong-Xing Wan, Hai Guo, Xiaowei Huang, Feiyue Lai, Jianhuang School of Data and Computer Science Sun Yat-sen University Guangzhou China YouTu Lab Tencent Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image matching task. However, how to find a set of person images according to a given attribute description, which is very practical in many surveillance applications, remains a rarely investigated cross-modality matching problem in person Re-ID. In this work, we present this challenge and formulate this task as a joint space learning problem. By imposing an attribute-guided attention mechanism for images and a semantic consistent adversary strategy for attributes, each modality, i.e., images and attributes, successfully learns semantically correlated concepts under the guidance of the other. We conducted extensive experiments on three attribute datasets and demonstrated that the proposed joint space learning method is so far the most effective method for the attribute-image cross-modality person Re-ID problem. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs

arXiv

引用

arXiv 2024年

作者： Liu, Yulong Yuan, Yunlong Wang, Chunwei Han, Jianhua Ma, Yongqiang Zhang, Li Zheng, Nanning Xu, Hang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi’an China School of Data Science Fudan University China Huawei Noah's Ark Lab Canada

The distinction between humans and animals lies in the unique ability of humans to use and create tools. Tools empower humans to overcome physiological limitations, fostering the creation of magnificent civilizations. Similarly, enabling foundational models like Large Language Models (LLMs) with the capacity to learn external tool usage may serve as a pivotal step toward realizing artificial general intelligence. Previous studies in this field have predominantly pursued two distinct approaches to augment the tool invocation capabilities of LLMs. The first approach emphasizes the construction of relevant datasets for model fine-tuning. The second approach, in contrast, aims to fully exploit the inherent reasoning abilities of LLMs through in-context learning strategies. In this work, we introduce a novel tool invocation pipeline designed to control massive real-world APIs. This pipeline mirrors the human task-solving process, addressing complicated real-life user queries. At each step, we guide LLMs to summarize the achieved results and determine the next course of action. We term this pipeline 'from Summary to action', Sum2Act for short. Empirical evaluations of our Sum2Act pipeline on the ToolBench benchmark show significant performance improvements, outperforming established methods like Re- Act and DFSDT. This highlights Sum2Act's effectiveness in enhancing LLMs for complex real-world tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Is L2 physics-informed loss always suitable for training physics-informed neural network? 22

Is L2 physics-informed loss always suitable for training phy...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chuwei Wang Shanda Li Di He Liwei Wang School of Mathematical Sciences Peking University Machine Learning Department School of Computer Science Carnegie Mellon University and Zhejiang Lab National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University

ISBN: (纸本)9781713871088

The Physics-Informed Neural Network (PINN) approach is a new and promising way to solve partial differential equations using deep learning. The L2 Physics- Informed Loss is the de-facto standard in training Physics-Informed Neural Networks. In this paper, we challenge this common practice by investigating the relationship between the loss function and the approximation quality of the learned solution. In particular, we leverage the concept of stability in the literature of partial differential equation to study the asymptotic behavior of the learned solution as the loss approaches zero. With this concept, we study an important class of high-dimensional non-linear PDEs in optimal control, the Hamilton-Jacobi- Bellman (HJB) Equation, and prove that for general Lp Physics-Informed Loss, a wide class of HJB equation is stable only if p is sufficiently large. Therefore, the commonly used L2 loss is not suitable for training PINN on those equations, while L∞ loss is a better choice. Based on the theoretical insight, we develop a novel PINN training algorithm to minimize the L∞ loss for HJB equations which is in a similar spirit to adversarial training. The effectiveness of the proposed algorithm is empirically demonstrated through experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embedding dynamic attributed networks by modeling the evolution processes

arXiv

引用

arXiv 2020年

作者： Xu, Zenan Ou, Zijing Su, Qinliang Yu, Jianxing Quan, Xiaojun Lin, Zhenkun School of Data and Computer Science Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embedding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real-world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks. Copyright © 2020, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Your transformer may not be as powerful as you expect 22

Your transformer may not be as powerful as you expect

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shengjie Luo Shanda Li Shuxin Zheng Tie-Yan Liu Liwei Wang Di He National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Zhejiang Lab Machine Learning Department School of Computer Science Carnegie Mellon University Microsoft Research National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University

ISBN: (纸本)9781713871088

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based Transformers is largely unexplored. In this work, we mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. One may naturally assume the answer is in the affirmative—RPE-based Transformers are universal function approximators. However, we present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. One key reason lies in that most RPEs are placed in the softmax attention that always generates a right stochastic matrix. This restricts the network from capturing positional information in the RPEs and limits its capacity. To overcome the problem and make the model more powerful, we first present sufficient conditions for RPE-based Transformers to achieve universal function approximation. With the theoretical guidance, we develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions. Therefore, the corresponding URPE-based Transformers become universal function approximators. Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications.

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：