Search

Your search keyword '"Li, Wanli"' showing total 783 results
Start Over Author "Li, Wanli"
783 results on '"Li, Wanli"'

1. DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks

Author

Zhang, Zeyu, Li, Lu, Wan, Shuyan, Wang, Sijie, Wang, Zhiyi, Lu, Zhiyuan, Hao, Dong, and Li, Wanli

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

The paper discusses signed graphs, which model friendly or antagonistic relationships using edges marked with positive or negative signs, focusing on the task of link sign prediction. While Signed Graph Neural Networks (SGNNs) have advanced, they face challenges like graph sparsity and unbalanced triangles. The authors propose using data augmentation (DA) techniques to address these issues, although many existing methods are not suitable for signed graphs due to a lack of side information. They highlight that the random DropEdge method, a rare DA approach applicable to signed graphs, does not enhance link sign prediction performance. In response, they introduce the Signed Graph Augmentation (SGA) framework, which includes a structure augmentation module to identify candidate edges and a strategy for selecting beneficial candidates, ultimately improving SGNN training. Experimental results show that SGA significantly boosts the performance of SGNN models, with a notable 32.3% improvement in F1-micro for SGCN on the Slashdot dataset., Comment: NeurIPS 2024

Published
2024

5. Generative Meta-Learning for Zero-Shot Relation Triplet Extraction

Author

Li, Wanli and Qian, Tieyun

Subjects
Computer Science - Computation and Language
Abstract

The zero-shot relation triplet extraction (ZeroRTE) task aims to extract relation triplets from a piece of text with unseen relation types. The seminal work adopts the pre-trained generative model to generate synthetic samples for new relations. However, current generative models lack the optimization process of model generalization on different tasks during training, and thus have limited generalization capability. For this reason, we propose a novel generative meta-learning framework which exploits the `learning-to-learn' ability of meta-learning to boost the generalization capability of generative models. Specifically, we first design a task-aware generative model which can learn the general knowledge by forcing the optimization process to be conducted across multiple tasks. Based on it, we then present three generative meta-learning approaches designated for three typical meta-learning categories. Extensive experimental results demonstrate that our framework achieves a new state-of-the-art performance for the ZeroRTE task.

Published
2023

6. Research on Path Planning of Concrete Pouring Construction Robot Based on Online Obstacle Avoidance Algorithm

Author

Fan, Siwen, Li, Wanli, Yin, Ruihao, Chaari, Fakher, Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Haddar, Mohamed, Series Editor, Cavas-Martínez, Francisco, Editorial Board Member, di Mare, Francesca, Editorial Board Member, Kwon, Young W., Editorial Board Member, Tolio, Tullio A. M., Editorial Board Member, Trojanowska, Justyna, Editorial Board Member, Schmitt, Robert, Editorial Board Member, Xu, Jinyang, Editorial Board Member, Halgamuge, Saman K., editor, Zhang, Hao, editor, Zhao, Dingxuan, editor, and Bian, Yongming, editor

Published
2024
Full Text
View/download PDF

7. Simulation Research on Cutting of Shield Machine Cutter Tool Based on Anisotropic Composite Materials

Author

Wang, Qiuping, Li, Wanli, Wang, Daozhi, Chaari, Fakher, Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Haddar, Mohamed, Series Editor, Cavas-Martínez, Francisco, Editorial Board Member, di Mare, Francesca, Editorial Board Member, Kwon, Young W., Editorial Board Member, Tolio, Tullio A. M., Editorial Board Member, Trojanowska, Justyna, Editorial Board Member, Schmitt, Robert, Editorial Board Member, Xu, Jinyang, Editorial Board Member, Halgamuge, Saman K., editor, Zhang, Hao, editor, Zhao, Dingxuan, editor, and Bian, Yongming, editor

Published
2024
Full Text
View/download PDF

11. From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction

Author

Li, Wanli and Qian, Tieyun

Subjects
Computer Science - Computation and Language
Abstract

Lack of labeled data is a main obstacle in relation extraction. Semi-supervised relation extraction (SSRE) has been proven to be a promising way for this problem through annotating unlabeled samples as additional training data. Almost all prior researches along this line adopt multiple models to make the annotations more reliable by taking the intersection set of predicted results from these models. However, the difference set, which contains rich information about unlabeled data, has been long neglected by prior studies. In this paper, we propose to learn not only from the consensus but also the disagreement among different models in SSRE. To this end, we develop a simple and general multi-teacher distillation (MTD) framework, which can be easily integrated into any existing SSRE methods. Specifically, we first let the teachers correspond to the multiple models and select the samples in the intersection set of the last iteration in SSRE methods to augment labeled data as usual. We then transfer the class distributions for samples in the difference set as soft labels to guide the student. We finally perform prediction using the trained student model. Experimental results on two public datasets demonstrate that our framework significantly promotes the performance of the base SSRE methods with pretty low computational cost.

Published
2021

23. Study of the Response of the Front-Row Far Side Dummy Under Vehicle Side Impact Condition

Author

Chen, Zixiao, Wang, Yanhao, Li, Wanli, Chen, Gaojun, Zhou, Chengjing, China Society of Automotive Engineers, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, and Zhang, Junjie James, Series Editor

Published
2023
Full Text
View/download PDF

26. Exploit Multiple Reference Graphs for Semi-supervised Relation Extraction

Author

Li, Wanli and Qian, Tieyun

Subjects
Computer Science - Computation and Language
Abstract

Manual annotation of the labeled data for relation extraction is time-consuming and labor-intensive. Semi-supervised methods can offer helping hands for this problem and have aroused great research interests. Existing work focuses on mapping the unlabeled samples to the classes to augment the labeled dataset. However, it is hard to find an overall good mapping function, especially for the samples with complicated syntactic components in one sentence. To tackle this limitation, we propose to build the connection between the unlabeled data and the labeled ones rather than directly mapping the unlabeled samples to the classes. Specifically, we first use three kinds of information to construct reference graphs, including entity reference, verb reference, and semantics reference. The goal is to semantically or lexically connect the unlabeled sample(s) to the labeled one(s). Then, we develop a Multiple Reference Graph (MRefG) model to exploit the reference information for better recognizing high-quality unlabeled samples. The effectiveness of our method is demonstrated by extensive comparison experiments with the state-of-the-art baselines on two public datasets.

Published
2020

31. Midcourse Guidance Trajectory Optimization of Interceptor Missile Based on Sequential Convex Programming

Author

Li Jiong, Zhang Jinlin, Shao Lei, Li Wanli, He Yangchao

Subjects
sequence convex programming, midcourse guidance, trajectory optimization, capture region, multiple constraints, hypersonic, interceptor, Motor vehicles. Aeronautics. Astronautics, TL1-4050
Abstract

Aiming at the trajectory optimization problem of interceptor midcourse guidance under strong nonlinear multi-constraint conditions, a trajectory optimization algorithm for fixed time constraints is proposed based on sequential convex programming method and capture region. Sequential convex optimization method has high computational efficiency for solving complex polynomials. However, in trajectory optimization problems, the strong nonlinearity of control variables and the convergence difficulty of fixed time terminal constraints are two main difficulties. Firstly, the problem is transformed into an affine system by using affine variables, and the affine system is convexized and discretized to solve the nonlinearity. Then, aiming at the problem that terminal constraints are difficult to converge in a fixed time, a weighted relaxation method of terminal constraints is proposed to transform the midcourse guidance problem into a sequence convex programming problem. The simulation results show that the proposed algorithm can quickly generate the midcourse guidance trajectory of interceptor that meets multiple constraints.

Published
2023
Full Text
View/download PDF

34. Study on impact resistance of Nano-Si[O.sub.2] reinforced STG/Kevlar composites

Author

Lin, Huan, Chen, Guojing, Li, Wanli, Cai, Lihai, and Liu, Wenyan

Subjects
Body armor -- Composition -- Mechanical properties, Composite materials -- Composition -- Structure -- Mechanical properties, Silicon compounds -- Usage, Engineering and manufacturing industries, Science and technology
Abstract

As a flexible protective material, shear thickening gel (STG)/Kevlar composite still has great potential to improve its impact resistance. In this paper, a novel STG/Si[O.sub.2]/Kevlar flexible protective composite was prepared by impregnating STG/Si[O.sub.2] into Kevlar. Due to the excellent Si[O.sub.2] enhancement effect, the STG/Si[O.sub.2]/Kevlar exhibited a higher safeguarding property than the STG/Kevlar. The maximum yam pull-out force of STG/Si[O.sub.2]/Kevlar reached 61.7 N, which was higher than the 41.9 N of STG/Kevlar. The uniform puncture results showed that the maximum bearing capacity of STG/Kevlar and STG/Si[O.sub.2]/Kevlar increased by 116.8% and 215.3%, respectively, compared with pure Kevlar. The impact test results indicated that 20 layers of STG/Si[O.sub.2]/Kevlar could not be penetrated by the knife stab and 24 layers of STG/Si[O.sub.2]/Kevlar could not be penetrated by 7.62 mm pistol bullets. Finally, the enhancement mechanism of impact resistance of STG/Si[O.sub.2]/Kevlar composites was studied. KEYWORDS composite material, impact resistance, particle enhancement, shear thickening gel (STG), 1 | INTRODUCTION Body armor or stab-resistant clothing is usually made of layers of high-performance fiber fabrics superimposed and sewn to achieve a protective effect, which seriously reduced the comfort [...]

Published
2022
Full Text
View/download PDF

38. The Vehicle Structure Response and Dummy Injury Research Based on C-IASI and C-NCAP Side-Impact Conditions

Author

Li, Wanli, Zhou, Chengjing, Chen, Gaojun, Zheng, Peichi, China Society of Automotive Engineers, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, and Zhang, Junjie James, Series Editor

Published
2022
Full Text
View/download PDF

39. Tracking Control of Hydraulic Circuit with Mulit-layer Winding Hoses Based on NB-ASMC with Input Time-Delay

Author

Qiang, Haiyan, Li, Wanli, Sun, Yougang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Jing, Xingjian, editor, Ding, Hu, editor, and Wang, Jiqiang, editor

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results