Efficiency and Scalability of Multi-lane Capsule Networks (MLCN)

Rosário, Vanderson Martins do; Breternitz, Maurício; Borin, Edson

doi:10.1109/sbac-pad.2019.00034

Cited by 8 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the node embedding layer, we obtain a set of node embedding matrix for each sub‐cascade graph, denoted as

boldS = {H_{1}, H_{2}, ⋯, H_{l}}

, where

boldS \in R^{l \times N \times K \times (2 F_{d} + F_{p})}

. Inspired by the work of capsule networks, 41,48–51 we design a capsule‐based hybrid aggregation layer to aggregate the learned node features from order‐level, node‐level, and graph‐level through dynamic routing, respectively.…”

Section: Methodsmentioning

confidence: 99%

Multi‐scale graph capsule with influence attention for information cascades prediction

Chen

Zhang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Information cascade size prediction is one of the primary challenges for understanding the diffusion of information. Traditional feature‐based methods heavily rely on the quality of handcrafted features, requiring extensive domain knowledge and hard to generalize to new domains. Recently, inspired by the success of deep learning in computer vision and natural language processing, researchers have developed neural network‐based approaches for tackling this problem. However, existing deep learning‐based methods either focused on modeling the temporal characteristics of cascades but ignored the structural information or failed to take the order‐scale and position‐scale into consideration in modeling structures of information propagation. This paper proposed a novel graph neural network‐based model, called MUCas, to learn the latent representations of cascade graphs from a multi‐scale perspective, which can make full use of the direction‐scale, high‐order‐scale, position‐scale, and dynamic‐scale of cascades via a newly designed MUlti‐scale Graph Capsule Network (MUG‐Caps) and the influence‐attention mechanism. Extensive experiments conducted on two real‐world data sets demonstrate that our MUCas significantly outperforms the state‐of‐the‐art approaches.

show abstract

“…From the node embedding layer, we obtain a set of node embedding matrix for each sub‐cascade graph, denoted as

boldS = {H_{1}, H_{2}, ⋯, H_{l}}

, where

boldS \in R^{l \times N \times K \times (2 F_{d} + F_{p})}

Section: Methodsmentioning

confidence: 99%

Multi‐scale graph capsule with influence attention for information cascades prediction

Chen

Zhang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…By varying the number of lanes and its size in the MLCN model, along with dropout trade-off for the classification for individual accuracy impact. In [17] they presented the loadbalancing problem of distributing heterogenous lanes in various accelerators to show that the simple greedy heuristic to deploy the lanes outperformed the naive random approach.…”

Section: IImentioning

confidence: 99%

Multi-Lane Capsule Network Architecture for Detection of COVID-19

Sridhar

Sanagavarapu

2021

2021 2nd International Conference on Intelligent Engineering and Management (ICIEM)

View full text Add to dashboard Cite

The COVID-19 pandemic in the world has given rise to a lot of research done in the field of medical imaging using deep learning and artificial intelligence methods for the detection and prognosis of the disease. Capsule Networks (CapsNet) perform image classification by identifying the spatial location and orientation of features within the images. In this paper, a Multi-lane Capsule Neural Networks (MLCN) model is introduced that performs dynamic routing networks with dimensionally distinct parallel lanes, replacing the traditional pooling operations in Convolutional Neural Networks (CNN). With the use of parallel capsules, feature orientation identification at any given part of the image is improved. The MLCN model has been studied in this paper using the X-ray images collected from patients tested for COVID-19 and its performance is evaluated using a number of metrics. It has been observed that the performance of the constructed CapsNet model achieved a testing accuracy of 96.8% with the F-1 score 97.19% performing better than the existing state-of-the-art models.

show abstract