45 citations · 141 across the 23 of their papers we have counts for
23 papers
Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models
Yingchun Wang, Jingcai Guo, Jie Zhang +3
Federated learning (FL) is an emerging technique that trains massive and geographically distributed edge data while maintaining privacy. However, FL has inherent challenges in term…
Tackling the Local Bias in Federated Graph Learning
Binchi Zhang, Minnan Luo, Shangbin Feng +3
Federated graph learning (FGL) has become an important research topic in response to the increasing scale and the distributed nature of graph-structured data in the real world. In…
Annotation of Chinese Predicate Heads and Relevant Elements
Yanping Chen, Wenfan Jin, Yongbin Qin +3
A predicate head is a verbal expression that plays a role as the structural center of a sentence. Identifying predicate heads is critical to understanding a sentence. It plays the…
Interpretation-enabled Software Reuse Detection Based on a Multi-Level Birthmark Model
Xi Xu, Qinghua Zheng, Zheng Yan +3
Software reuse, especially partial reuse, poses legal and security threats to software development. Since its source codes are usually unavailable, software reuse is hard to be det…
Towards Entity Alignment in the Open World: An Unsupervised Approach
Weixin Zeng, Xiang Zhao, Jiuyang Tang +3
Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs). It is a pivotal step for integrating KGs to increase knowledge coverage and qual…
A Boundary Regression Model for Nested Named Entity Recognition
Yanping Chen, Lefei Wu, Qinghua Zheng +7
Recognizing named entities (NEs) is commonly conducted as a classification problem that predicts a class tag for a word or a NE candidate in a sentence. In shallow structures, cate…
XTQA: Span-Level Explanations of the Textbook Question Answering
Jie Ma, Qi Chai, Jun Liu +3
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. We a…
SeqTrans: Automatic Vulnerability Fix via Sequence to Sequence Learning
Jianlei Chi, Yu Qu, Ting Liu +2
Software vulnerabilities are now reported at an unprecedented speed due to the recent development of automated vulnerability hunting tools. However, fixing vulnerabilities still ma…
Self-Weighted Robust LDA for Multiclass Classification with Edge Classes
Caixia Yan, Xiaojun Chang, Minnan Luo +4
Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are p…
TaxThemis: Interactive Mining and Exploration of Suspicious Tax Evasion Group
Yating Lin, Kamkwai Wong, Yong Wang +4
Tax evasion is a serious economic problem for many countries, as it can undermine the government' s tax system and lead to an unfair business competition environment. Recent resear…
DWMD: Dimensional Weighted Orderwise Moment Discrepancy for Domain-specific Hidden Representation Matching
Rongzhe Wei, Fa Zhang, Bo Dong +1
Knowledge transfer from a source domain to a different but semantically related target domain has long been an important topic in the context of unsupervised domain adaptation (UDA…
Scalable Attack on Graph Data by Injecting Vicious Nodes
Jihong Wang, Minnan Luo, Fnu Suya +3
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…
Self-Supervised Graph Representation Learning via Global Context Prediction
Zhen Peng, Yixiang Dong, Minnan Luo +2
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 supe…
Graph Representation Learning via Graphical Mutual Information Maximization
Zhen Peng, Wenbing Huang, Minnan Luo +4
The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expres…
Enjoy the Untrusted Cloud: A Secure, Scalable and Efficient SQL-like Query Framework for Outsourcing Data
Yaxing Chen, Qinghua Zheng, Dan Liu +5
While the security of the cloud remains a concern, a common practice is to encrypt data before outsourcing them for utilization. One key challenging issue is how to efficiently per…
Knowledge forest: a novel model to organize knowledge fragments
Qinghua Zheng, Jun Liu, Hongwei Zeng +3
With the rapid growth of knowledge, it shows a steady trend of knowledge fragmentization. Knowledge fragmentization manifests as that the knowledge related to a specific topic in a…
Modeling e-Learners' Cognitive and Metacognitive Strategy in Comparative Question Solving
Feng Tian, Jia Yue, Kuo-ming Chao +7
Cognitive and metacognitive strategy had demonstrated a significant role in self-regulated learning (SRL), and an appropriate use of strategies is beneficial to effective learning…
Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models
Yan Zeng, Yangyang Lan, Yazhou Hao +2
Neural sequence models have achieved great success in sentence-level sentiment classification. However, some models are exceptionally complex or based on expensive features. Some o…
Learning Unit State Recognition Based on Multi-channel Data Fusion
Feng Tian, Jia Yue, Xing Wan +2
Despite recent advances in MOOC, the current e-learning systems have advantages of alleviating barriers by time differences, and geographically spatial separation between teachers…
Simple to Complex Cross-modal Learning to Rank
Minnan Luo, Xiaojun Chang, Zhihui Li +3
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a r…
Joint Hacking and Latent Hazard Rate Estimation
Ziqi Liu, Alexander J. Smola, Kyle Soska +2
In this paper we describe an algorithm for predicting the websites at risk in a long range hacking activity, while jointly inferring the provenance and evolution of vulnerabilities…
Attributing Hacks
Ziqi Liu, Alexander J. Smola, Kyle Soska +3
In this paper we describe an algorithm for estimating the provenance of hacks on websites. That is, given properties of sites and the temporal occurrence of attacks, we are able to…
Truth Discovery to Resolve Object Conflicts in Linked Data
Wenqiang Liu
In the community of Linked Data, anyone can publish their data as Linked Data on the web because of the openness of the Semantic Web. As such, RDF (Resource Description Framework)…