Degree distributions under general node removal: Power-law or Poisson?

Lee, Mi Jin; Kim, Jung-Ho; Goh, K.-I.; Lee, Sang Hoon; Son, Seung‐Woo; Lee, Deok-Sun

doi:10.1103/physreve.106.064309

Cited by 3 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This layer generates the initial embedding vector from the user-item interaction graph using a random wandering matrix factorization. For large undirected network graphs such as recommendation data, the interaction information is very unevenly distributed and usually follows a power-law distribution [11]. Random walks enable the graph to have a topological structure that can well overcome the power-law distribution.…”

Section: Node Initial Embedding Layermentioning

confidence: 99%

See 1 more Smart Citation

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

Gu,

Xu,

Liu

2024

ITC

View full text Add to dashboard Cite

A graph neural network-based recommendation system treats the relationship between user items as a graph, and achieves deep feature mining by modelling the graph nodes. However, the complexity of the features of graph neural network-based recommendation systems brings poor interpretability and suffers from data sparsity problems. To address the above problems, a graph convolutional neural network recommendation model (RWESA-GNNR) based on random walk embedding combined with sentiment analysis is proposed. Firstly, a random walk-based matrix factorization is designed as the initial embedding. Secondly, the user and item nodes are modelled using a convolutional neural network with an injected attention mechanism. Then, sentiment analysis is performed on the review text, and attention mechanism is introduced to fuse text sentiment features and semantic features. Finally, node features and text features are aggregated to generate recommendation results. The experimental results show that our proposed algorithm outperforms traditional recommendation algorithms and other graph neural network-based recommendation algorithms in terms of recommendation results, with an improvement of about 2.43%-5.75%.

show abstract

Section: Node Initial Embedding Layermentioning

confidence: 99%

“…We connect the final interaction node features obtained from Equation (11) with the final sentiment features obtained from Equation ( 17) to obtain the final representation U of the user and the final representation I of the item, as shown in Equation (18):…”

Section: Prediction Modulementioning

confidence: 99%

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

Gu,

Xu,

Liu

2024

ITC

View full text Add to dashboard Cite

show abstract

“…where G is the de Gennes factor. The applicability of de Gennes scaling for isostructural compounds with exclusive RE 3 + magnetic moments has been investigated extensively, see e. g.. [46][47][48][49][50][51] For our series of compounds RESi 3 with RE = Tb to Tm and, for completeness, also HoSi 3 [33] and GdSi 3 , [32] T N is plotted against G (Figure 8), where T N is obtained from magnetic susceptibility measurements χ ac (T). Obviously, excellent scaling is observed.…”

Section: Magnetic Susceptibilitymentioning

confidence: 99%

“…[46] More importantly, the mean field approach underlying the de Gennes scaling neglects possible important influences on the magnetic properties of materials, including crystalline electric field (CEF) effects and anisotropic exchange. [47,51,52] The excellent de Gennes scaling in RESi 3 may point towards a negligible impact of these latter contributions.…”

Section: Magnetic Susceptibilitymentioning

confidence: 99%

Crystal Structure and Magnetic Properties of High‐Pressure Phases RESi₃ (RE=Tb, Dy, Er, Tm)

Neziraj,

Akselrud,

Wirth

et al. 2023

Zeitschrift anorg allge chemie

View full text Add to dashboard Cite

The new metastable binary rare‐earth metal trisilicides RESi3 (RE = Tb, Dy, Er, and Tm) are obtained by high‐pressure high‐temperature synthesis (9.5 GPa, 823‐923 K). Powder diffraction data refinements reveal that their crystal structure is isotypic to that of YbSi3, and the values of cell parameters and cell volumes decrease from Tb to Tm. Magnetic measurements on the compounds indicate Curie‐Weiss paramagnetic behavior and antiferromagnetic ordering at low temperatures. The values for TN follow a de Gennes scaling indicating coupling of the magnetic moments via conduction electrons. Upon heating at ambient pressure, the RESi3 compounds decompose into Si and RESi2‐x.

show abstract

“…This includes strengthening network monitoring, implementing efficient intrusion detection and protection mechanisms, and enhancing data privacy protection. Only through effective measures and technical means can we ensure the safe operation of the power system and protect the interests of users[2][3]. Therefore, in order to ensure the safe operation of the power system, preventing and detecting the tampering of topological nodes becomes an urgent problem.…”

mentioning

confidence: 99%

Power system topological node tamper detection method based on fuzzy graph theory

Tan,

Guo,

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Power system involves a large number of nodes and lines, and the topology is very complex. In such a complex network, node tamper detection needs to consider a variety of combinations and connection modes, which increases the complexity of the problem. Therefore, a new method of topological node tamper detection based on fuzzy graph theory is proposed. The feature difference values of topological nodes are extracted according to the node tampering feature vector. Detection of topological node similarity based on fuzzy graph-neural network. Based on this, the cost function of topological node tampering is established to obtain the Bayesian estimate of the tampering coefficient of the topological node transmission channel, and the detection of topological node tampering is completed. The experimental results show that the application time of the research method is shorter, the detection of power node tampering behavior is more comprehensive, and the tampering success rate is higher.

show abstract

Degree distributions under general node removal: Power-law or Poisson?

Cited by 3 publications

References 56 publications

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

Crystal Structure and Magnetic Properties of High‐Pressure Phases RESi₃ (RE=Tb, Dy, Er, Tm)

Power system topological node tamper detection method based on fuzzy graph theory

Contact Info

Product

Resources

About

Degree distributions under general node removal: Power-law or Poisson?

Cited by 3 publications

References 56 publications

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

RWESA-GNNR: Fusing Random Walk Embedding and Sentiment Analysis for Graph Neural Network Recommendation

Crystal Structure and Magnetic Properties of High‐Pressure Phases RESi3 (RE=Tb, Dy, Er, Tm)

Power system topological node tamper detection method based on fuzzy graph theory

Contact Info

Product

Resources

About

Crystal Structure and Magnetic Properties of High‐Pressure Phases RESi₃ (RE=Tb, Dy, Er, Tm)