Hierarchical Attention Signed Network

Wu, Yong; Wang, Binjun; Li, Wei

doi:10.1109/icispc51671.2020.00018

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, approaches such as employing classical PCA for dimensionality reduction, including nonlinear dimensionality reduction, would first input the matrix according to the graph's network information. LLE [7], a Laplacian algorithm based on widely accepted assumptions [8], and directed graph approaches [9]. Given an adjacency matrix, the LLE algorithm depicts each node as a linearly weighted neighboring node, calculates the node's rebuilt weight matrix, and then transforms it to an eigenvalue solution.…”

Section: Introductionmentioning

confidence: 99%

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Alshara

2022

Security and Communication Networks

View full text Add to dashboard Cite

Although a strategy for predicting stock prices using relational data has been described recently, no practical way for selecting aggregating various forms of relational data to forecast stock prices has been discovered. The authors present an upgraded multilayer node graph attention network (FHAN) model that incorporates the Fraudar algorithm and provides insight into the interaction between several items. The model, which regards businesses as nodes and interactions as edges, aggregates data from various connection types and adds it to each company’s node representation, which is then automatically fed into the task-specific layer select information. The testing findings indicate that this approach is more accurate in stock price prediction than the currently popular neural network methodology. The experiment compares several distinct neural network algorithms. This approach is more accurate than the previous method when ideal parameters are used. The average rise is around 4%, while the largest increase is 24%.

show abstract

Section: Introductionmentioning

confidence: 99%

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Alshara

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Moreover, we also have {d i ir } k i=1 and {h i ir } k i=1 for the subset E T V,ir . The selected knowledge-enhanced entity representations with modal-agnostic semantic features f a T and f a V are further fused by utilizing the signed attention mechanism [19,38], in order to simultaneously capture both high-order consistent and inconsistent entity correlations. Specifically, KEC adopts the positive attention to capture the consistent correlation with respect to the post contents.…”

Section: Knowledge-enhanced Entity Correlationmentioning

confidence: 99%

Yang Chengzong and the University of Science and Technology of China

Liu

Zhang

2018

Cultures of Science

View full text Add to dashboard Cite

Yang Chengzong was a famous radiochemist and is considered the founding father of radiochemistry in China. He was also a pioneer in the field of natural uranium technology and was one of the founders of the University of Science and Technology of China (USTC). Professor Yang planned and participated in the establishment of the university and its relocation to Hefei, Anhui Province, making indispensable contributions to the development of USTC. This article describes his more than 30 years of experience in scientific and educational endeavours at USTC and explores the important roles he played in the development of the university.

show abstract