no code implementations • CCL 2020 • Peiyao Zhao, Qinghua Zheng, Bo Dong, Jianfei Ruan, Minnan Luo
税收是国家赖以生存的物质基础。为加快税收现代化, 方便纳税人便捷、规范开具增值税发票, 国税总局规定纳税人在税控系统开票前选择发票明细对应的税收分类才可正常开具发票。提高税收分类的准确度, 是构建税收风险指标和分析纳税人行为特征的重要基础。基于此, 本文提出了一种基于有向异构图的短文本分类模型(Heterogeneous Directed Graph Attenton Network, HDGAT), 利用发票明细间的有向信息建模, 引入外部知识, 显著地提高了发票明细的税收分类准确度。
1 code implementation • 8 Mar 2024 • Haochen Han, Qinghua Zheng, Guang Dai, Minnan Luo, Jingdong Wang
To achieve this, we propose L2RM, a general framework based on Optimal Transport (OT) that learns to rematch mismatched pairs.
no code implementations • 2 Mar 2024 • Junxian Li, Bin Shi, Erfei Cui, Hua Wei, Qinghua Zheng
To the best of our knowledge, it is the first work to include hidden layer distillation for student MLP on graphs and to combine graph Positional Encoding with MLP.
no code implementations • 3 Nov 2023 • Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang, Qinghua Zheng
Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models.
1 code implementation • 24 Oct 2023 • Wenkai Shi, Wenbin An, Feng Tian, Qinghua Zheng, Qianying Wang, Ping Chen
New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents.
1 code implementation • 16 Oct 2023 • Wenbin An, Feng Tian, Wenkai Shi, Yan Chen, Qinghua Zheng, Qianying Wang, Ping Chen
Specifically, we retrieve k-nearest neighbors of a query as its positive keys to capture semantic similarities between data and then aggregate information from the neighbors to learn compact cluster representations, which can make fine-grained categories more separatable.
no code implementations • 26 Sep 2023 • Zhihao Zhang, YiWei Chen, Weizhan Zhang, Caixia Yan, Qinghua Zheng, Qi Wang, Wangdu Chen
Viewport prediction is a crucial aspect of tile-based 360 video streaming system.
1 code implementation • ICCV 2023 • Tuo Feng, Wenguan Wang, Xiaohan Wang, Yi Yang, Qinghua Zheng
The mined patterns are, in turn, used to repaint the embedding space, so as to respect the underlying distribution of the entire training dataset and improve the robustness to the variations.
1 code implementation • 30 Jun 2023 • Zijian Cai, Zhaoxuan Tan, Zhenyu Lei, Zifeng Zhu, Hongrui Wang, Qinghua Zheng, Minnan Luo
For datasets without graph structure, we simply replace the GNN with an MLP, which has also shown strong performance.
no code implementations • 16 Jun 2023 • Yuntao Shou, Xiangyong Cao, Deyu Meng, Bo Dong, Qinghua Zheng
By setting a matching weight and calculating attention scores between modal features row by row, LMAM contains fewer parameters than the self-attention method.
no code implementations • 19 May 2023 • Yingchun Wang, Jingcai Guo, Yi Liu, Song Guo, Weizhan Zhang, Xiangyong Cao, Qinghua Zheng
Based on the idea that in-distribution (ID) data with spurious features may have a lower experience risk, in this paper, we propose a novel Spurious Feature-targeted model Pruning framework, dubbed SFP, to automatically explore invariant substructures without referring to the above drawbacks.
1 code implementation • 22 Apr 2023 • Heng Wang, Wenqian Zhang, Yuyang Bai, Zhaoxuan Tan, Shangbin Feng, Qinghua Zheng, Minnan Luo
We then propose MVSD, a novel Multi-View Spoiler Detection framework that takes into account the external knowledge about movies and user activities on movie review platforms.
1 code implementation • CVPR 2023 • Haochen Han, Kaiyao Miao, Qinghua Zheng, Minnan Luo
Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data.
no code implementations • 9 Feb 2023 • Yingchun Wang, Jingcai Guo, Jie Zhang, Song Guo, Weizhan Zhang, Qinghua Zheng
Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy.
no code implementations • 29 Nov 2022 • Zhuohang Dang, Jihong Wang, Minnan Luo, Chengyou Jia, Caixia Yan, Qinghua Zheng
To these challenges, we propose a novel Information Bottleneck (IB) based Disentangled Generation Framework for FSL, termed as DisGenIB, that can simultaneously guarantee the discrimination and diversity of generated samples.
2 code implementations • 28 Nov 2022 • Wenbin An, Feng Tian, Qinghua Zheng, Wei Ding, Qianying Wang, Ping Chen
Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance.
no code implementations • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang, Hsien-Kai Kuo, Yu-Syuan Xu, Man-Yu Lee, Allen Lu, Chia-Ming Cheng, Chih-Cheng Chen, Jia-Ying Yong, Hong-Han Shuai, Wen-Huang Cheng, Zhuang Jia, Tianyu Xu, Yijian Zhang, Long Bao, Heng Sun, Diankai Zhang, Si Gao, Shaoli Liu, Biao Wu, Xiaofeng Zhang, Chengjian Zheng, Kaidi Lu, Ning Wang, Xiao Sun, HaoDong Wu, Xuncheng Liu, Weizhan Zhang, Caixia Yan, Haipeng Du, Qinghua Zheng, Qi Wang, Wangdu Chen, Ran Duan, Mengdi Sun, Dan Zhu, Guannan Chen, Hojin Cho, Steve Kim, Shijie Yue, Chenghua Li, Zhengyang Zhuge, Wei Chen, Wenxu Wang, Yufeng Zhou, Xiaochen Cai, Hengxing Cai, Kele Xu, Li Liu, Zehua Cheng, Wenyi Lian, Wenjing Lian
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
1 code implementation • 15 Oct 2022 • Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo
Extensive experiments demonstrate that PAR is better at augmenting political text understanding and successfully advances the state-of-the-art in political perspective detection and roll call vote prediction.
1 code implementation • 14 Oct 2022 • Wenbin An, Feng Tian, Ping Chen, Siliang Tang, Qinghua Zheng, Qianying Wang
Novel category discovery aims at adapting models trained on known categories to novel categories.
1 code implementation • 18 Aug 2022 • Xinshun Feng, Herun Wan, Shangbin Feng, Hongrui Wang, Jun Zhou, Qinghua Zheng, Minnan Luo
Further experiments bear out the quality of node representations learned with GraTO and the effectiveness of model architecture.
1 code implementation • 17 Aug 2022 • Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng, Zilong Chen, Jundong Li, Qinghua Zheng, Minnan Luo
In addition, given the stealing behavior of novel Twitter bots, BIC proposes to model semantic consistency in tweets based on attention weights while using it to augment the decision process.
1 code implementation • 17 Aug 2022 • Shujie Yang, Binchi Zhang, Shangbin Feng, Zhaoxuan Tan, Qinghua Zheng, Jun Zhou, Minnan Luo
In light of this problem, we propose AHEAD: a heterogeneity-aware unsupervised graph anomaly detection approach based on the encoder-decoder framework.
1 code implementation • 16 Aug 2022 • Zhaoxuan Tan, Zilong Chen, Shangbin Feng, Qingyue Zhang, Qinghua Zheng, Jundong Li, Minnan Luo
Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion.
1 code implementation • 9 Jun 2022 • Shangbin Feng, Zhaoxuan Tan, Herun Wan, Ningnan Wang, Zilong Chen, Binchi Zhang, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, Xinshun Feng, Qingyue Zhang, Hongrui Wang, YuHan Liu, Yuyang Bai, Heng Wang, Zijian Cai, Yanbo Wang, Lijing Zheng, Zihan Ma, Jundong Li, Minnan Luo
Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse.
1 code implementation • 20 May 2022 • Qinghua Zheng, Jihong Wang, Minnan Luo, YaoLiang Yu, Jundong Li, Lina Yao, Xiaojun Chang
Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}"
no code implementations • 16 May 2022 • Haochen Han, Qinghua Zheng, Minnan Luo, Kaiyao Miao, Feng Tian, Yan Chen
To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence.
no code implementations • 27 Mar 2022 • Chengyou Jia, Minnan Luo, Caixia Yan, Xiaojun Chang, Qinghua Zheng
On the other hand, there are numerous unpaired persons in real-world scene images.
no code implementations • 21 Jan 2022 • Jihong Wang, Minnan Luo, Jundong Li, Ziqi Liu, Jun Zhou, Qinghua Zheng
Our RGIB attempts to learn robust node representations against adversarial perturbations by preserving the original information in the benign graph while eliminating the adversarial information in the adversarial graph.
no code implementations • 22 Oct 2021 • Binchi Zhang, Minnan Luo, Shangbin Feng, Ziqi Liu, Jun Zhou, Qinghua Zheng
In light of these problems, we propose a Privacy-Preserving Subgraph sampling based distributed GCN training method (PPSGCN), which preserves data privacy and significantly cuts back on communication and memory overhead.
no code implementations • 4 Sep 2021 • Caixia Yan, Xiaojun Chang, Minnan Luo, Huan Liu, Xiaoqin Zhang, Qinghua Zheng
To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection.
Ranked #4 on Zero-Shot Object Detection on MS-COCO
Contrastive Learning Generalized Zero-Shot Object Detection +3
1 code implementation • 9 Aug 2021 • Shangbin Feng, Zilong Chen, Wenqian Zhang, Qingyao Li, Qinghua Zheng, Xiaojun Chang, Minnan Luo
Specifically, we construct a political knowledge graph to serve as domain-specific external knowledge.
1 code implementation • 9 Aug 2021 • Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo
Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks.
no code implementations • 23 Mar 2021 • Yanping Chen, Wenfan Jin, Yongbin Qin, Ruizhang Huang, Qinghua Zheng, Ping Chen
This annotation guideline emphasizes the role of the predicate as the structural center of a sentence.
1 code implementation • 26 Jan 2021 • Weixin Zeng, Xiang Zhao, Jiuyang Tang, Xinyi Li, Minnan Luo, Qinghua Zheng
These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment.
1 code implementation • 29 Nov 2020 • Yanping Chen, Lefei Wu, Qinghua Zheng, Ruizhang Huang, Jun Liu, Liyuan Deng, Junhui Yu, Yongbin Qing, Bo Dong, Ping Chen
Then, a regression operation is introduced to regress boundaries of NEs in a sentence.
1 code implementation • 25 Nov 2020 • Jie Ma, Qi Chai, Jun Liu, Qingyu Yin, Pinghui Wang, Qinghua Zheng
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
no code implementations • 24 Sep 2020 • Caixia Yan, Xiaojun Chang, Minnan Luo, Qinghua Zheng, Xiaoqin Zhang, Zhihui Li, Feiping Nie
In this regard, a novel self-weighted robust LDA with l21-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.
no code implementations • 18 Jul 2020 • Rongzhe Wei, Fa Zhang, Bo Dong, Qinghua Zheng
Our metric function takes advantage of a series for high-order moment alignment, and we theoretically prove that our DWMD metric function is error-free, which means that it can strictly reflect the distribution differences between domains and is valid without any feature distribution assumption.
1 code implementation • 22 Apr 2020 • Jihong Wang, Minnan Luo, Fnu Suya, Jundong Li, Zijiang Yang, Qinghua Zheng
Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations.
no code implementations • 3 Mar 2020 • Zhen Peng, Yixiang Dong, Minnan Luo, Xiao-Ming Wu, Qinghua Zheng
To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself.
1 code implementation • 4 Feb 2020 • Zhen Peng, Wenbing Huang, Minnan Luo, Qinghua Zheng, Yu Rong, Tingyang Xu, Junzhou Huang
The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision.
no code implementations • 18 Dec 2019 • Yaxing Chen, Qinghua Zheng, Dan Liu, Zheng Yan, Wenhai Sun, Ning Zhang, Wenjing Lou, Y. Thomas Hou
On one hand, such work lacks of supporting scalable access control over multiple data users.
Cryptography and Security Databases Distributed, Parallel, and Cluster Computing
no code implementations • 14 Dec 2019 • Qinghua Zheng, Jun Liu, Hongwei Zeng, Zhaotong Guo, Bei Wu, Bifan Wei
Facet trees can organize knowledge fragments with facet hyponymy to alleviate information overload.
no code implementations • 4 Jun 2019 • Feng Tian, Jia Yue, Kuo-Ming Chao, Buyue Qian, Nazaraf Shah, Longzhuang Li, Haiping Zhu, Yan Chen, Bin Zeng, Qinghua Zheng
from "The C Programming Language" course and "What are similarities and differences between packet switching and circuit switching?"
no code implementations • 4 Feb 2017 • Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval.
1 code implementation • 7 Nov 2016 • Ziqi Liu, Alexander J. Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng, Jun Zhou
That is, given properties of sites and the temporal occurrence of attacks, we are able to attribute individual attacks to joint causes and vulnerabilities, as well as estimating the evolution of these vulnerabilities over time.