Soft hypergraph for modeling global interactions via social media networks

Amini, Abbas; Firouzkouhi, Narjes; Gholami, Ahmad; Gupta, Anju; Cheng, Chun; Davvaz, Bijan

doi:10.1016/j.eswa.2022.117466

Cited by 10 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent times, hypergraph learning has witnessed substantial advancements in addressing problems, which involve relationships among data extending beyond pairwise interactions. Applications span diverse domains, including visual object recognition [22], trafc prediction [23], recommender systems [24], and social networks [25]. In the context of stock recommendation tasks, the utilization of hypergraphs involves categorizing stocks into multiple groups and refning their representations.…”

Section: Related Workmentioning

confidence: 99%

A Static-Dynamic Hypergraph Neural Network Framework Based on Residual Learning for Stock Recommendation

Hao,

Liu,

Sun

et al. 2024

Complexity

View full text Add to dashboard Cite

Stock ranking prediction is an effective method for achieving a high investment return and plays a crucial role in investment decisions. However, previous studies have overlooked the interconnections among stocks or have solely relied on predefined graphs for stock relationship information. The predefined graphs may not capture all possible relationships and may not be suitable for describing dynamic relationships. To address these issues, we propose a Static-Dynamic hypergraph neural network framework based on Residual Learning (SD-RL). Compared with traditional methods, SD-RL has the following advantages. (1) Stocks are no longer treated as isolated entities; instead, their static and dynamic relationship information is taken into account. (2) Leveraging the data-driven methodology, SD-RL autonomously learns both the static graph and dynamic hypergraph through dedicated graph learning and hypergraph learning modules, respectively. (3) By employing residual learning, various latent relationship information flows are mined, which enhances the stock embedding’s capacity to capture trends. Extensive experiments on the real data verify the effectiveness of our proposed methods.

show abstract

Section: Related Workmentioning

confidence: 99%

A Static-Dynamic Hypergraph Neural Network Framework Based on Residual Learning for Stock Recommendation

Hao,

Liu,

Sun

et al. 2024

Complexity

View full text Add to dashboard Cite

show abstract

“…Indeed, a hypergraph is a useful tool to analyze the structure of a system that connects a group of elements (more than two elements) together, and in this sense, it can play an important role in embedding, classifying, partitioning, covering, and clustering elements in different classes. Therefore, a hypergraph as an extension and covering of the graph has attracted the attention of many researchers, and this theory has spread rapidly, especially since it has many applications in real world (its uses in model gene interactions (ER-type hypergraph [2]), machine learning (spectral hypergraph [3]), computer networks (WIS hypergraph [4]), chemistry (molecular hypergraph [5]), visual classification (hypergraph-induced convolutional network [6]), and social media (soft hypergraph [7])). Because of the more important and updated hypergraphs, a hypergraph structure as a hypernetwork has various applications, among which it can refer to updated works such as soft hypergraph for modeling global interactions via social media networks [7], session-based recommendation with hypergraph convolutional networks and sequential information embeddings [8], hypergraph-based analysis and design of intelligent collaborative manufacturing space [9] and hypergraph-based centrality metrics for maritime container service networks: a worldwide application [10].…”

Section: Introductionmentioning

confidence: 99%

Decision Making Based on Valued Fuzzy Superhypergraphs

Hamidi,

Smarandache,

Taghinezhad

2024

CMES

View full text Add to dashboard Cite

This paper explores the defects in fuzzy (hyper) graphs (as complex (hyper) networks) and extends the fuzzy (hyper) graphs to fuzzy (quasi) superhypergraphs as a new concept. We have modeled the fuzzy superhypergraphs as complex superhypernetworks in order to make a relation between labeled objects in the form of details and generalities. Indeed, the structure of fuzzy (quasi) superhypergraphs collects groups of labeled objects and analyzes them in the form of the part to part of objects, the part of objects to the whole group of objects, and the whole to the whole group of objects at the same time. We have investigated the properties of fuzzy (quasi) superhypergraphs based on any positive real number as valued fuzzy (quasi) superhypergraphs, considering the complement of valued fuzzy (quasi) superhypergraphs, the notation of isomorphism of valued fuzzy (quasi) superhypergraphs based on the permutations, and we have presented the isomorphic conditions of (self complemented) valued fuzzy (quasi) superhypergraphs. The concept of impact membership value of fuzzy (quasi) superhypergraphs is introduced in this study and it is applied in designing the real problem in the real world. Finally, the problem of business superhypernetworks is presented as an application of fuzzy valued quasi superhypergraphs in the real world.

show abstract

“…Therefore, complex networks based on simple graphs are no longer applicable for performing and computing collective dynamics in complex social systems. Social relations with group bonds require new forms of network structure depictions to express their properties and behaviors [ 41 ].…”

Section: Introductionmentioning

confidence: 99%

“…Other studies like collective cooperation [ 48 ], ecological networks [ 49 ], and disease predictions [ 50 ] are proven high accuracy utilizing hypernetwork structures. Hypernetworks have currently been broadly applied to model social media networks [ 41 ], music recommendation systems [ 51 ], choice dilemmas [ 52 ], and other dynamic models [ 53 , 54 ].…”

Section: Introductionmentioning

confidence: 99%

A hypernetwork-based urn model for explaining collective dynamics

Lu,

Du,

2023

PLoS ONE

View full text Add to dashboard Cite

The topological characterization of complex systems has significantly contributed to our understanding of the principles of collective dynamics. However, the representation of general complex networks is not enough for explaining certain problems, such as collective actions. Considering the effectiveness of hypernetworks on modeling real-world complex networks, in this paper, we proposed a hypernetwork-based Pólya urn model that considers the effect of group identity. The mathematical deduction and simulation experiments show that social influence provides a strong imitation environment for individuals, which can prevent the dynamics from being self-correcting. Additionally, the unpredictability of the social system increases with growing social influence, and the effect of group identity can moderate market inequality caused by individual preference and social influence. The present work provides a modeling basis for a better understanding of the logic of collective dynamics.

show abstract

Soft hypergraph for modeling global interactions via social media networks

Cited by 10 publications

References 41 publications

A Static-Dynamic Hypergraph Neural Network Framework Based on Residual Learning for Stock Recommendation

A Static-Dynamic Hypergraph Neural Network Framework Based on Residual Learning for Stock Recommendation

Decision Making Based on Valued Fuzzy Superhypergraphs

A hypernetwork-based urn model for explaining collective dynamics

Contact Info

Product

Resources

About