Search

Your search keyword '"Han, Zhiwei"' showing total 745 results
Start Over Author "Han, Zhiwei"
745 results on '"Han, Zhiwei"'

1. Towards a Unified Framework of Contrastive Learning for Disentangled Representations

Author

Matthes, Stefan, Han, Zhiwei, and Shen, Hao

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual contrastive losses, such as noise-contrastive estimation (NCE) and InfoNCE, and rely on specific assumptions about the data generating process. This paper extends the theoretical guarantees for disentanglement to a broader family of contrastive methods, while also relaxing the assumptions about the data distribution. Specifically, we prove identifiability of the true latents for four contrastive losses studied in this paper, without imposing common independence assumptions. The theoretical findings are validated on several benchmark datasets. Finally, practical limitations of these methods are also investigated.

Published
2023

9. Recent Progress in Atmospheric Chemistry Research in China: Establishing a Theoretical Framework for the “Air Pollution Complex”

Author

Zhu, Tong, Tang, Mingjin, Gao, Meng, Bi, Xinhui, Cao, Junji, Che, Huizheng, Chen, Jianmin, Ding, Aijun, Fu, Pingqing, Gao, Jian, Gao, Yang, Ge, Maofa, Ge, Xinlei, Han, Zhiwei, He, Hong, Huang, Ru-Jin, Huang, Xin, Liao, Hong, Liu, Cheng, Liu, Huan, Liu, Jianguo, Liu, Shaw Chen, Lu, Keding, Ma, Qingxin, Nie, Wei, Shao, Min, Song, Yu, Sun, Yele, Tang, Xiao, Wang, Tao, Wang, Tijian, Wang, Weigang, Wang, Xuemei, Wang, Zifa, Yin, Yan, Zhang, Qiang, Zhang, Weijun, Zhang, Yanlin, Zhang, Yunhong, Zhao, Yu, Zheng, Mei, Zhu, Bin, and Zhu, Jiang

Published
2023
Full Text
View/download PDF

18. Metapath- and Entity-aware Graph Neural Network for Recommendation

Author

Anwaar, Muhammad Umer, Han, Zhiwei, Arumugaswamy, Shyam, Khan, Rayyan Ahmad, Weber, Thomas, Qiu, Tianming, Shen, Hao, Liu, Yuanting, and Kleinsteuber, Martin

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

In graph neural networks (GNNs), message passing iteratively aggregates nodes' information from their direct neighbors while neglecting the sequential nature of multi-hop node connections. Such sequential node connections e.g., metapaths, capture critical insights for downstream tasks. Concretely, in recommender systems (RSs), disregarding these insights leads to inadequate distillation of collaborative signals. In this paper, we employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs, which explicitly capture sequential semantics in graph structures. We propose meta\textbf{P}ath and \textbf{E}ntity-\textbf{A}ware \textbf{G}raph \textbf{N}eural \textbf{N}etwork (PEAGNN), which trains multilayer GNNs to perform metapath-aware information aggregation on such subgraphs. This aggregated information from different metapaths is then fused using attention mechanism. Finally, PEAGNN gives us the representations for node and subgraph, which can be used to train MLP for predicting score for target user-item pairs. To leverage the local structure of CSGs, we present entity-awareness that acts as a contrastive regularizer on node embedding. Moreover, PEAGNN can be combined with prominent layers such as GAT, GCN and GraphSage. Our empirical evaluation shows that our proposed technique outperforms competitive baselines on several datasets for recommendation tasks. Further analysis demonstrates that PEAGNN also learns meaningful metapath combinations from a given set of metapaths.

Published
2020

20. Interactive Image Restoration

Author

Han, Zhiwei, Weber, Thomas, Matthes, Stefan, Liu, Yuanting, and Shen, Hao

Subjects
Computer Science - Human-Computer Interaction, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Machine learning and many of its applications are considered hard to approach due to their complexity and lack of transparency. One mission of human-centric machine learning is to improve algorithm transparency and user satisfaction while ensuring an acceptable task accuracy. In this work, we present an interactive image restoration framework, which exploits both image prior and human painting knowledge in an iterative manner such that they can boost on each other. Additionally, in this system users can repeatedly get feedback of their interactions from the restoration progress. This informs the users about their impact on the restoration results, which leads to better sense of control, which can lead to greater trust and approachability. The positive results of both objective and subjective evaluation indicate that, our interactive approach positively contributes to the approachability of restoration algorithms in terms of algorithm performance and user experience., Comment: Human-centric Machine Learning Workshop, NeurIPS 2019

Published
2019

26. Swin Transformer-Based Positioning Methodology for Catenary Support Components in High-Speed Railway

Author

Wang, Hui, Guo, Weiping, Zhong, Junping, Han, Zhiwei, Liu, Zhigang, 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, Liang, Jianying, editor, Liu, Zhigang, editor, Diao, Lijun, editor, and An, Min, editor

Published
2022
Full Text
View/download PDF

27. Detection Approach Based on an Improved Yolov5 for Catenary Support Components

Author

Zhao, Ranran, Han, Zhiwei, Liu, Zhigang, 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, Liang, Jianying, editor, Liu, Zhigang, editor, Diao, Lijun, editor, and An, Min, editor

Published
2022
Full Text
View/download PDF

28. A Review of Research Progress of Isotope Technology in Tracing Pollution Process in the Mine Environment

Author

ZHAO Ruihan, HAN Zhiwei, and FU Yong

Subjects
mine environment, isotopes, mc-icp-ms, acidification process, heavy metals, Geology, QE1-996.5, Ecology, QH540-549.5
Abstract

BACKGROUND With mining activities taking place on a global scale, the concern for environmental issues within and around mines continues to increase. The advent of multi-collector inductively coupled plasma-mass spectrometry (MC-ICP-MS) has promoted the geochemical study of isotopes and has led to the widespread use of isotope tracing techniques to investigate various issues in the mining environment. OBJECTIVES To systematically summarize the various types of studies currently conducted on the application of isotope tracing technology in mining environments, with the aim of highlighting the importance of the application of isotope tracing technology in complex mining environments and the diversity of scientific problems it can solve. METHODS Data published by scholars at home and abroad by July 2022 has been collected and compiled on testing and analyzing the supply source/connection of mine water body, sulfate/carbonate source and the cause of acid mine wastewater (AMD), migration and transformation of mining elements, different sources and contribution rates of heavy metal pollution with the help of isotope tracer technology. The study area covers more than 40 regions in 20 countries. RESULTS It is found that hydrogen and oxygen isotope tracing techniques in water bodies are effective tools for mine water source analysis, hydraulic linkage studies and AMD source identification. Sulfate sulfur and oxygen isotope tracing techniques provide important support for the study of sulfate sources in mine environments, AMD acidification processes and pollution, bacterial sulfate reduction and elemental migration transformation. Heavy metal isotope (Pb, Cd, Zn, Hg isotopes) tracing technology is an effective way to investigate the sources of metal pollution in mines and nearby environments and the contribution of different sources. CONCLUSIONS Although isotope techniques play an important role in resolving the sources of environmental pollutants in mines and the mechanisms of migration and transformation of characteristic pollutants and revealing the hydrogeochemical processes in mines, most of the current studies are limited to the application of single/few isotopes for short time tracing studies of environmental media in mines. Therefore, further development of multi-isotope tracing technology is needed in the future, as well as long-term and continuous monitoring and investigation of various problems in the mine environment. New and effective methods for pollution prevention and control are also proposed.

Published
2022
Full Text
View/download PDF

41. Reducing Adversarial Examples Through Boundary Methods

Author

Hu, Xinyi, Zhang, Zhengming, Liu, Zhouyong, Han, Zhiwei, Yang, Luxi, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Fang, Lu, editor, Chen, Yiran, editor, Zhai, Guangtao, editor, Wang, Jane, editor, Wang, Ruiping, editor, and Dong, Weisheng, editor

Published
2021
Full Text
View/download PDF

42. Unsupervised Learning of Joint Embeddings for Node Representation and Community Detection

Author

Khan, Rayyan Ahmad, Anwaar, Muhammad Umer, Kaddah, Omran, Han, Zhiwei, Kleinsteuber, Martin, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Oliver, Nuria, editor, Pérez-Cruz, Fernando, editor, Kramer, Stefan, editor, Read, Jesse, editor, and Lozano, Jose A., editor

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results