Graph Representation Learning Meets Computer Vision: A Survey

Jiao, Licheng; Chen, Jie; Liu, Fang; Yang, Shuyuan; You, Chao; Liu, Xu; Hou, Biao

doi:10.1109/tai.2022.3194869

Cited by 31 publications

(8 citation statements)

References 152 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In computer graphics and in computer vision -including subdomains such as virtual reality, geographic information systems, and autonomous driving -two types of sensing data have become increasingly prevalent [302]- [305]. First, using light detection and ranging (LiDAR) sensing, the external surfaces of objects are often represented with 3D point clouds and their physical coordinates (and possibly color information).…”

Section: E Computer Graphics and Computer Visionmentioning

confidence: 99%

Graph Filters for Signal Processing and Machine Learning on Graphs

Isufi¹,

Gama²,

Shuman³

et al. 2022

Preprint

View full text Add to dashboard Cite

Filters are fundamental in extracting information from data. For time series and image data that reside on Euclidean domains, filters are the crux of many signal processing and machine learning techniques, including convolutional neural networks. Increasingly, modern data also reside on networks and other irregular domains whose structure is better captured by a graph. To process and learn from such data, graph filters account for the structure of the underlying data domain. In this article, we provide a comprehensive overview of graph filters, including the different filtering categories, design strategies for each type, and trade-offs between different types of graph filters. We discuss how to extend graph filters into filter banks and graph neural networks to enhance the representational power; that is, to model a broader variety of signal classes, data patterns, and relationships. We also showcase the fundamental role of graph filters in signal processing and machine learning applications. Our aim is that this article serves the dual purpose of providing a unifying framework for both beginner and experienced researchers, as well as a common understanding that promotes collaborations between signal processing, machine learning, and application domains.

show abstract

Section: E Computer Graphics and Computer Visionmentioning

confidence: 99%

Graph Filters for Signal Processing and Machine Learning on Graphs

Isufi¹,

Gama²,

Shuman³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently graph representation learning has received a lot of attention and researchers have carried out extensive research to obtain a better representation of nodes ( Generale, Blume & Cochez, 2022 ). Jiao et al (2022) classified graph representation learning into the non-neural network and neural network approaches and collated relevant applications of graph representation learning in computer vision tasks, Shurrab & Duwairi (2022) proposed to combine self-supervised learning and computer vision to be able to better handle computer vision tasks.…”

Section: Introductionmentioning

confidence: 99%

Application of graph auto-encoders based on regularization in recommendation algorithms

Xie

Wen

Pang

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Social networking has become a hot topic, in which recommendation algorithms are the most important. Recently, the combination of deep learning and recommendation algorithms has attracted considerable attention. The integration of autoencoders and graph convolutional neural networks, while providing an effective solution to the shortcomings of traditional algorithms, fails to take into account user preferences and risks over-smoothing as the number of encoder layers increases. Therefore, we introduce L1 and L2 regularization techniques and fuse them linearly to address user preferences and over-smoothing. In addition, the presence of a large amount of noisy data in the graph data has an impact on feature extraction. To our best knowledge, most existing models do not account for noise and address the problem of noisy data in graph data. Thus, we introduce the idea of denoising autoencoders into graph autoencoders, which can effectively address the noise problem. We demonstrate the capability of the proposed model on four widely used datasets and experimentally demonstrate that our model is more competitive by improving up to 1.3, 1.4, and 1.2, respectively, on the edge prediction task.

show abstract

“…1). These include social network analysis [40], molecular and drug discovery [41], bioinformatics [42], computer vision [43], language processing [44], materials science, and chemistry [45], as well as more recent advances in internet of things [46,47], energy systems [48,49], intelligent transportation systems [50,51], power systems [52], wireless networks [53], and communication systems [54].…”

Section: Introductionmentioning

confidence: 99%

From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics

Li,

Xue,

Zargari

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Graph theory within power electronics, developed over a 50-year span, is continually evolving, necessitating ongoing research endeavors. Facing with the never-been-seen explosion of graphstructured data, the state-of-the-art deep learning technique-Graph Neural Networks (GNNs), becomes the leading trend in machine learning within just recent five years and demonstrated surprisingly broad and prominent benefits covering from new drug discovery to better IC design. However, its promising applications in Power Electronics are still rarely discussed and its full potential remains unexplored. Addressing this gap, this review paper is the first to outline GNNs' general workflow in power electronics, laying the groundwork and examining current GNN methodologies within the field. To bridge the gap in the sparse GNN literature within this domain, we also provide extended discussions on leveraging insights from GNN-aided circuit design to enrich power electronics research. Our work includes in-depth GNNbased case studies that demonstrate promising applications from converters to system-level power electronics, showcasing GNNs' unique benefits and untapped possibilities (e.g., accurate component design, voltage predictions on IEEE-13 bus and 118 bus systems). Additionally, we provide a comprehensive survey of GNNs' latest and successful applications, emphasizing their impact on energy-centric sectors, such as transportation electrification, smart grids. Considering the interdisciplinary nature of power electronics in modern energy systems, our review highlights the potential of GNNs emerge as a promising tool to decode the intricate behavior and dynamics of power electronics systems, and we hope such synergies between advanced AI methodologies like GNNs with the ever-evolving graph theory can lead to more powerful tools, novel methodologies, and advancements in the power electronics community.

show abstract

Graph Representation Learning Meets Computer Vision: A Survey

Cited by 31 publications

References 152 publications

Graph Filters for Signal Processing and Machine Learning on Graphs

Graph Filters for Signal Processing and Machine Learning on Graphs

Application of graph auto-encoders based on regularization in recommendation algorithms

From Graph Theory to Graph Neural Networks (GNNs): The Opportunities of GNNs in Power Electronics

Contact Info

Product

Resources

About