Search

Your search keyword '"Liu, Weiqi"' showing total 667 results
Start Over Author "Liu, Weiqi"
667 results on '"Liu, Weiqi"'

4. Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing

Author

Chen, Jie, Liu, Weiqi, Huang, Zhizhong, Gao, Junbin, Zhang, Junping, and Pu, Jian

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

The performance of GNNs degrades as they become deeper due to the over-smoothing. Among all the attempts to prevent over-smoothing, residual connection is one of the promising methods due to its simplicity. However, recent studies have shown that GNNs with residual connections only slightly slow down the degeneration. The reason why residual connections fail in GNNs is still unknown. In this paper, we investigate the forward and backward behavior of GNNs with residual connections from a novel path decomposition perspective. We find that the recursive aggregation of the median length paths from the binomial distribution of residual connection paths dominates output representation, resulting in over-smoothing as GNNs go deeper. Entangled propagation and weight matrices cause gradient smoothing and prevent GNNs with residual connections from optimizing to the identity mapping. Based on these findings, we present a Universal Deep GNNs (UDGNN) framework with cold-start adaptive residual connections (DRIVE) and feedforward modules. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art results over non-smooth heterophily datasets by simply stacking standard GNNs.

Published
2022

5. Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination

Author

Chen, Jie, Liu, Weiqi, and Pu, Jian

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

Message passing is a fundamental procedure for graph neural networks in the field of graph representation learning. Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process. However, real-world graphs tend to be noisy and/or non-smooth. The homophily assumption does not always hold, leading to sub-optimal results. A revised message passing method needs to maintain each node's discriminative ability when aggregating the message from neighbors. To this end, we propose a Memory-based Message Passing (MMP) method to decouple the message of each node into a self-embedding part for discrimination and a memory part for propagation. Furthermore, we develop a control mechanism and a decoupling regularization to control the ratio of absorbing and excluding the message in the memory for each node. More importantly, our MMP is a general skill that can work as an additional layer to help improve traditional GNNs performance. Extensive experiments on various datasets with different homophily ratios demonstrate the effectiveness and robustness of the proposed method., Comment: Accepted by ICASSP 2022

Published
2022

21. Origami/Kirigami-Inspired Reconfigurable 6R Linkages and Tessellations

Author

Liu, Weiqi, Chen, Yan, Chaari, Fakher, Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Cavas-Martínez, Francisco, Editorial Board Member, di Mare, Francesca, Editorial Board Member, Haddar, Mohamed, Editorial Board Member, Kwon, Young W., Editorial Board Member, Trojanowska, Justyna, Editorial Board Member, Xu, Jinyang, Editorial Board Member, and Liu, Xinjun, editor

Published
2023
Full Text
View/download PDF

22. Fault-Tolerant Control for Five-Phase Permanent Magnet Synchronous Motor Servo System Based on Topological Reconstruction

Author

Han, Jiwen, Song, Hongzhou, Liu, Yinan, Pei, Xiaqing, Zheng, Zaiping, Liu, Weiqi, Zheng, Zheng, Editor-in-Chief, Xi, Zhiyu, Associate Editor, Gong, Siqian, Series Editor, Hong, Wei-Chiang, Series Editor, Mellal, Mohamed Arezki, Series Editor, Narayanan, Ramadas, Series Editor, Nguyen, Quang Ngoc, Series Editor, Ong, Hwai Chyuan, Series Editor, Sun, Zaicheng, Series Editor, Ullah, Sharif, Series Editor, Wu, Junwei, Series Editor, Zhang, Baochang, Series Editor, Zhang, Wei, Series Editor, Zhu, Quanxin, Series Editor, Zheng, Wei, Series Editor, Yan, Liang, editor, and Na, Jing, editor

Published
2023
Full Text
View/download PDF

30. A Low Complexity Quantum Principal Component Analysis Algorithm

Author

He, Chen, Li, Jiazhen, Liu, Weiqi, and Wang, Z. Jane

Subjects
Quantum Physics
Abstract

In this paper, we propose a low complexity quantum principal component analysis (qPCA) algorithm. Similar to the state-of-the-art qPCA, it achieves dimension reduction by extracting principal components of the data matrix, rather than all components of the data matrix, to quantum registers, so that samples of measurement required can be reduced considerably. However, the major advantage of our qPCA over the state-of-the-art qPCA is that it requires much less quantum gates. In addition, it is more accurate due to the simplification of the quantum circuit. We implement the proposed qPCA on the IBM quantum computing platform, and the experimental results are consistent with our expectations.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results