1 code implementation • ACL 2022 • Biru Zhu, Yujia Qin, Fanchao Qi, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu
To validate our viewpoints, we design two methods to evaluate the robustness of FMS: (1) model disguise attack, which post-trains an inferior PTM with a contrastive objective, and (2) evaluation data selection, which selects a subset of the data points for FMS evaluation based on K-means clustering.
no code implementations • 31 May 2024 • Zhuonan Zheng, Sheng Zhou, Hongjia Xu, Ming Gu, Yilun Xu, Ao Li, Yuhong Li, Jingjun Gu, Jiajun Bu
Both the homophilous and heterophilous patterns are propagated with a novel semantic-aware message passing mechanism.
Ranked #7 on Node Classification on Wisconsin
1 code implementation • 28 May 2024 • Zhuonan Zheng, Yuanchen Bei, Sheng Zhou, Yao Ma, Ming Gu, Hongjia Xu, Chengyu Lai, Jiawei Chen, Jiajun Bu
Based on HTMP and empirical analysis, we reveal that the success of message passing in existing HTGNNs is attributed to implicitly enhancing the compatibility matrix among classes.
no code implementations • 8 May 2024 • Gang Hu, Ming Gu
This paper introduces a hybrid approach combining Markowitz's portfolio theory with reinforcement learning, utilizing knowledge distillation for training agents.
1 code implementation • 8 Feb 2024 • Meihan Liu, Zeyu Fang, Zhen Zhang, Ming Gu, Sheng Zhou, Xin Wang, Jiajun Bu
Motivated by our empirical analysis, we reevaluate the role of GNNs in graph domain adaptation and uncover the pivotal role of the propagation process in GNNs for adapting to different graph domains.
1 code implementation • 30 Jan 2024 • Ming Gu, Yan Yang, Chengcai Chen, Zhou Yu
Experimental results on the MultiWOZ 2. 1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters.
1 code implementation • 4 Jan 2024 • Shengtao Li, Ge Gao, Yudong Liu, Yu-Shen Liu, Ming Gu
Our method maximizes the spatial expressiveness of grid features and maintains computational efficiency.
no code implementations • 21 Dec 2023 • Han Huang, Yulun Wu, Junsheng Zhou, Ge Gao, Ming Gu, Yu-Shen Liu
To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint.
1 code implementation • 10 Aug 2023 • Ming Gu, Gaoming Yang, Sheng Zhou, Ning Ma, Jiawei Chen, Qiaoyu Tan, Meihan Liu, Jiajun Bu
Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results.
no code implementations • 2 Dec 2022 • Hairong Luo, Ge Gao, Han Huang, ZiYi Ke, Cheng Peng, Ming Gu
It can be supplemented using deep learning.
1 code implementation • 7 Oct 2022 • Zhuoer Xu, Guanghui Zhu, Changhua Meng, Shiwen Cui, ZhenZhe Ying, Weiqiang Wang, Ming Gu, Yihua Huang
In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.
1 code implementation • CVPR 2022 • Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, Liqing Zhang
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings.
document understanding Optical Character Recognition (OCR) +1
no code implementations • 4 Mar 2022 • Han Liu, Xiaoyu Song, Ge Gao, Hehua Zhang, Yu-Shen Liu, Ming Gu
Semantic rule checking on RDFS/OWL data has been widely used in the construction industry.
no code implementations • 29 Sep 2021 • Michael Yeh, Ming Gu
For $m\times n$ matrices where a few principal components explain most of the variance in the data, we develop one such algorithm that runs in $O(mnl)$ time, where $l\ll \min(m, n)$ is a small multiple of the number of principal components.
1 code implementation • NeurIPS 2019 • Han Liu, Zhizhong Han, Yu-Shen Liu, Ming Gu
Low-rank metric learning aims to learn better discrimination of data subject to low-rank constraints.
no code implementations • 13 Apr 2018 • Jianwei Xiao, Ming Gu, Julien Langou
In contrast, randomized QRCP (RQRCP) algorithms have proven themselves empirically to be highly competitive with high-performance implementations of QR in processing time, on uniprocessor and shared memory machines, and as reliable as QRCP in pivot quality.
Numerical Analysis
no code implementations • 6 Mar 2018 • Yuehua Feng, Jianwei Xiao, Ming Gu
We present Flip-Flop Spectrum-Revealing QR (Flip-Flop SRQR) factorization, a significantly faster and more reliable variant of the QLP factorization of Stewart, for low-rank matrix approximations.
Numerical Analysis Numerical Analysis 15A18, 15A23, 65F99
1 code implementation • Proceedings 2001 IEEE International Conference on Data Mining 2002 • Chris H.Q. Ding, Xiaofeng He, Hongyuan Zhab, Ming Gu, Horst D. Simon
In this paper, we propose a new algorithm for graph partitioning with an objective function that follows the min-max clustering principle.