Related references
Note: Only part of the references are listed.
Article
Computer Science, Theory & Methods
Jiamin Chen et al.
Summary: Graph Neural Architecture Search (Auto-GNAS) is an automatic machine learning framework that efficiently and automatically constructs graph neural networks with satisfactory model performance. Through parallel estimation and multiple genetic searchers, Auto-GNAS achieves competitive models performance and better search efficiency compared to existing algorithms.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Lu Bai et al.
Summary: In this paper, a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model is proposed for learning effective features for graph classification. This model addresses the issues of information loss and imprecise information representation in existing spatially-based graph convolutional network (GCN) models, and bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models. Experimental results demonstrate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Luca Pasa et al.
Summary: The paper proposes a novel strategy to generate independent representations for neighboring nodes at different topological distances using a single graph convolution layer, highlighting the limitation of stacking multiple non-linear graph convolutions.
Article
Computer Science, Information Systems
Babatounde Moctard Oloulade et al.
Summary: This paper provides a comprehensive review of automatic GNN model building frameworks to facilitate future progress. The complexity of GNN model components poses challenges to existing GNN efficiency, leading to the development of automated machine learning frameworks for finding the best GNN models.
TSINGHUA SCIENCE AND TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Zonghan Wu et al.
Summary: This article provides a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. It discusses the taxonomy of GNNs, their applications, and summarizes open-source codes, benchmark data sets, and model evaluation. The article also proposes potential research directions in this rapidly growing field.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Jiye Liang et al.
Summary: This paper introduces a framework for graph-based semi-supervised learning by dynamically improving the quality of the graph, integrating graph construction and label inference for dynamic improvement. The proposed framework is general and can embed most existing GSSL methods to enhance their performance.
Article
Computer Science, Artificial Intelligence
Tomoki Yoshida et al.
Summary: The paper introduces a supervised distance metric learning method for graph classification, called interpretable graph metric learning (IGML). IGML learns discriminative metrics in a subgraph-based feature space, utilizes a sparsity-inducing penalty to identify important subgraphs, and guarantees solution optimality. Additionally, a pruning technique based on safe screening and working set selection methods is proposed for the large number of optimization variables in the formulation.
Article
Computer Science, Artificial Intelligence
Gustav Sourek et al.
Summary: The framework provides a unified representation of neural models based on logic programming and allows for easy extension of GNN models. In experiments, the framework demonstrated correctness and computation efficiency.
Proceedings Paper
Computer Science, Artificial Intelligence
Yiwei Wang et al.
Summary: Graph neural networks (GNNs) can benefit from a curriculum learning approach similar to human learning process, for which the CurGraph framework is proposed to analyze the difficulty of graphs and provide a smooth transition from easy to hard graphs using the smooth-step method. CurGraph significantly improves performance of popular GNN models on graph classification tasks.
PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Shaofei Cai et al.
Summary: This paper introduces Graph Neural Architecture Search (GNAS) to automatically learn better architecture and optimal message-passing depth for graph neural networks (GNNs). Experiments demonstrate that GNAS can search for improved GNNs with multiple message-passing mechanisms on five large-scale datasets for three classical graph tasks, outperforming state-of-the-art manual and search-based GNNs.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Information Systems
Jiamin Chen et al.
Summary: This paper proposes a parallel graph architecture search (GraphPAS) framework for graph neural networks, which explores the search space in parallel using sharing-based evolution learning and dynamically adopts architecture information entropy for mutation selection probability to improve search efficiency and accuracy.
SIGIR '21 - PROCEEDINGS OF THE 44TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Rui Shi et al.
Summary: This study proposes using a surrogate model for estimating network accuracy, reducing training time and improving search efficiency by comparing network performance through a comparator.
2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
Huan Zhao et al.
Summary: This study proposes a framework called SANE to automatically design data-specific GNN architectures and address the challenges in search space design and cost facing by NAS methods. By designing a novel search space and a differentiable search algorithm, SANE outperforms existing GNN models and NAS approaches in terms of effectiveness and efficiency.
2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Minji Yoon et al.
20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020)
(2020)
Article
Computer Science, Theory & Methods
John T. Hancock et al.
JOURNAL OF BIG DATA
(2020)
Article
Computer Science, Artificial Intelligence
Kien Do et al.
Editorial Material
Engineering, Electrical & Electronic
Michael M. Bronstein et al.
IEEE SIGNAL PROCESSING MAGAZINE
(2017)
Article
Mathematics, Interdisciplinary Applications
Zouhair Ben Jemaa et al.
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS
(2015)
Article
Computer Science, Artificial Intelligence
Werner Uwents et al.
Article
Computer Science, Information Systems
Salvador Garcia et al.
INFORMATION SCIENCES
(2010)
Article
Biochemical Research Methods
KM Borgwardt et al.
Article
Computer Science, Artificial Intelligence
BJ Jain et al.
Article
Biochemistry & Molecular Biology
I Schomburg et al.
NUCLEIC ACIDS RESEARCH
(2004)
Article
Biochemistry & Molecular Biology
PD Dobson et al.
JOURNAL OF MOLECULAR BIOLOGY
(2003)
Article
Chemistry, Multidisciplinary
JJ Sutherland et al.
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
(2003)
