相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Information Systems
Yintao Yang et al.
Summary: CGA2TC is a new graph-based model for text classification that combines contrastive learning and adaptive augmentation strategy to obtain more robust node representation. It constructs a text graph using word co-occurrence and document word relationships and designs an augmentation strategy to solve the noise problem and preserve essential structures. The model handles labeled and unlabeled nodes differently and adopts random sampling to reduce resource consumption. Experimental results demonstrate the effectiveness of CGA2TC in text classification tasks.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Cong Xu et al.
Summary: This study aims to predict whether a stock that hits its daily price limit will also close at the same price level, and proposes a novel hierarchical graph neural network (HGNN) to improve the prediction accuracy. Experimental results show that the method outperforms state-of-the-art solutions in terms of accuracy and return ratio.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Sanjay Kumar et al.
Summary: With the boom in technologies and mobile networks, online social networks have become integral and influential in our daily lives. This paper proposes a novel method of influence maximization using graph embedding and graph neural networks, which outperforms previous methods according to experimental results on real-life networks.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Yi Wang et al.
Summary: Traffic flow forecasting is crucial for transportation, and this paper proposes an attention-based spatiotemporal graph attention network (ASTGAT) model that captures dynamic spatiotemporal correlations and deepens the network for improved prediction accuracy.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Hao Peng et al.
Summary: In this article, the authors propose a novel multi-relational Graph Neural Network architecture called RIOGNN, which addresses the complexity and diversity issues in heterogeneous graphs. By using reinforced, recursive, and flexible neighborhood selection, RIOGNN achieves more discriminative node embeddings with enhanced explainability. It also demonstrates advancements in effectiveness and efficiency compared to other comparative GNN models.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Yintao Yang et al.
Summary: This study introduces a new graph-based text classification model CGA2TC, which utilizes contrastive learning and adaptive augmentation strategy for more robust node representation. By exploring word co-occurrence and document word relationships to construct a text graph, diverse augmentation strategies are employed to address noise issues. Consistency training is applied on labeled and unlabeled nodes, demonstrating the effectiveness of the model in text classification tasks.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Fan Wu et al.
Summary: This paper introduces a novel shilling attack model called GOAT, which combines primitive attack methods and upgraded attack ideas, using a generative adversarial network and graph convolution structure to generate fake ratings, balancing feasibility and effectiveness.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Andreas Holzinger et al.
Summary: AI excels in certain tasks but humans excel at multi-modal thinking and building self-explanatory systems. The medical domain highlights the importance of various modalities contributing to one result. Using conceptual knowledge to guide model training can lead to more explainable, robust, and less biased machine learning models.
INFORMATION FUSION
(2021)
Article
Computer Science, Information Systems
Jie Wang et al.
Summary: The proposed mixed-order graph convolutional networks (MOGCN) address the oversmoothing issue and underutilization of pseudo-labels of unlabeled nodes in semi-supervised learning. MOGCN consists of two modules: constructing multiple GCN learners with multi-order adjacency matrices and employing a novel ensemble module to efficiently combine results from these learners. Experimental results on three public benchmark datasets demonstrate that MOGCN consistently outperforms state-of-the-art methods.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Shirin Noekhah et al.
INFORMATION PROCESSING & MANAGEMENT
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Yizhu Jiao et al.
20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020)
(2020)
Proceedings Paper
Computer Science, Information Systems
Zhen Peng et al.
WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020)
(2020)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Le Lv et al.
2019 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR FINANCIAL ENGINEERING & ECONOMICS (CIFER 2019)
(2019)