DeGTeC: A deep graph-temporal clustering framework for data-parallel job characterization in data centers

Liang, Yi; Chen, Kaizhong; Liang, Yi; Su, Xing; Jin, Xiaoming

doi:10.1016/j.future.2022.11.014

Cited by 6 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous systems in nature and society can be characterized as complex networks [1][2][3] , such as World Wide Web, social networks, and biological networks, in which nodes represent entities and the connections between them are represented as edges or links (In this article, complex networks are depicted as graphs, with the terms 'edge' and 'link' being used interchangeably to signify the connections or relationships between nodes within the network. Furthermore, the terms 'graph' and 'network' both represent the same structural concept and are not differentiated in the context of this paper).…”

Section: Incorporating High-frequency Information Into Edge Convoluti...mentioning

confidence: 99%

Incorporating high-frequency information into edge convolution for link prediction in complex networks

Zhang,

Xu,

Zhu

2024

Sci Rep

View full text Add to dashboard Cite

Link prediction in complex networks aims to mine hidden or to-be-generated links between network nodes, which plays a significant role in fields such as the cold start of recommendation systems, knowledge graph completion and biomedical experiments. The existing link prediction models based on graph neural networks, such as graph convolution neural networks, often only learn the low-frequency information reflecting the common characteristics of nodes while ignoring the high-frequency information reflecting the differences between nodes when learning node representation, which makes the corresponding link prediction models show over smoothness and poor performance. Focusing on links in complex networks, this paper proposes an edge convolutional graph neural network EdgeConvHiF that fuses high-frequency node information to achieve the representation learning of links so that link prediction can be realized by implementing the classification of links. EdgeConvHiF can also be employed as a baseline, and extensive experiments on real-world benchmarks validate that EdgeConvHiF not only has high stability but also has more advantages than the existing representative baselines.

show abstract

Section: Incorporating High-frequency Information Into Edge Convoluti...mentioning

confidence: 99%

Incorporating high-frequency information into edge convolution for link prediction in complex networks

Zhang,

Xu,

Zhu

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

An ensemble clustering approach for modeling hidden categorization perspectives for cloud workloads

Daraghmeh,

Agarwal,

Jararweh

2023

Cluster Comput

View full text Add to dashboard Cite

Multi-objective optimization-based workflow scheduling for applications with data locality and deadline constraints in geo-distributed clouds

Wu,

Wang,

Wang

et al. 2024

Future Generation Computer Systems

View full text Add to dashboard Cite

DeGTeC: A deep graph-temporal clustering framework for data-parallel job characterization in data centers

Cited by 6 publications

References 16 publications

Incorporating high-frequency information into edge convolution for link prediction in complex networks

Incorporating high-frequency information into edge convolution for link prediction in complex networks

An ensemble clustering approach for modeling hidden categorization perspectives for cloud workloads

Multi-objective optimization-based workflow scheduling for applications with data locality and deadline constraints in geo-distributed clouds

Contact Info

Product

Resources

About