Graph Neural Networks for Bidirected and Multidirected Graphs: A Formal Review
DOI:
https://doi.org/10.59846/ajbas.v4i2.832الملخص
Graph-structured data often exhibit complex edge semantics beyond simple undirected links—such as one‐way flows, independent endpoint orientations, or multiple parallel arcs. While standard Graph Neural Networks (GNNs) handle undirected and directed graphs, they cannot fully exploit richer topologies like bidirected or multidirected graphs. We introduce two novel GNN variants: Bidirected GNNs, which separately aggregate messages according to endpoint‐specific arrow assignments, and Multidirected GNNs, which incorporate parallel‐edge counts into feature updates. We present formal definitions, derive update rules, and showcase illustrative examples to demonstrate each model’s ability to encode complex orientation and multiplicity patterns. Our frameworks pave the way for more expressive graph representation learning in domains requiring fine‐grained edge semantics.
المراجع
[1] Jonathan L Gross, Jay Yellen, and Mark Anderson. Graph theory and its applications. Chapman and Hall/CRC, 2018.
[2] Guillaume Verdon, Trevor McCourt, Enxhell Luzhnica, Vikash Singh, Stefan Leichenauer, and Jack Hidary. Quantum graph neural
networks. arXiv preprint arXiv:1909.12264, 2019.
[3] Lilas Alrahis and Ozgur Sinanoglu. Graph neural networks for hardware vulnerability analysis-can you trust your gnn? In 2023
IEEE 41st VLSI Test Symposium (VTS), pages 1–4. IEEE, 2023.
[4] Mingyu Guan, Anand Padmanabha Iyer, and Taesoo Kim. Dynagraph: dynamic graph neural networks at scale. In Proceedings of
the 5th ACM SIGMOD Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network
Data Analytics (NDA), pages 1–10, 2022.
[5] Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. Skeleton-based action recognition with directed graph neural networks. In
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7912–7921, 2019.
[6] Yixuan He, Quan Gan, David Wipf, Gesine D Reinert, Junchi Yan, and Mihai Cucuringu. Gnnrank: Learning global rankings
from pairwise comparisons via directed graph neural networks. In international conference on machine learning, pages 8581–8612.
PMLR, 2022.
[7] Yixuan He, Gesine Reinert, David Wipf, and Mihai Cucuringu. Robust angular synchronization via directed graph neural networks.
arXiv preprint arXiv:2310.05842, 2023.
[8] Guo Zhenyu and Zhang Wanhong. An efficient inference schema for gene regulatory networks using directed graph neural networks.
In 2023 42nd Chinese Control Conference (CCC), pages 6829–6834. IEEE, 2023.
[9] Ping Zhang and Gary Chartrand. Introduction to graph theory. Tata McGraw-Hill, 2:2–1, 2006.
[10] Frank Gurski, Carolin Rehs, and Jochen Rethmann. Directed path-width of sequence digraphs. In International Conference on
Combinatorial Optimization and Applications, pages 79–93. Springer, 2018.
[11] Takaaki Fujita and Florentin Smarandache. Superhypergraph neural networks and plithogenic graph neural networks: Theoretical
foundations. Infinite Study, 2025.
[12] Rui Li, Xin Yuan, Mohsen Radfar, Peter Marendy, Wei Ni, Terrence J O’Brien, and Pablo M Casillas-Espinosa. Graph signal
processing, graph neural network and graph learning on biological data: a systematic review. IEEE Reviews in Biomedical
Engineering, 16:109–135, 2021.
[13] Amer Marwan El-Samman, Ince Amina Husain, Mai Huynh, Stefano De Castro, Brooke Morton, and Stijn De Baerdemacker. Global ´
geometry of chemical graph neural network representations in terms of chemical moieties. Digital Discovery, 3(3):544–557, 2024.
[14] Xiaojun Kang, Xinchuan Li, Hong Yao, Dan Li, Bo Jiang, Xiaoyue Peng, Tiejun Wu, Shihua Qi, and Lijun Dong. Dynamic
hypergraph neural networks based on key hyperedges. Information Sciences, 616:37–51, 2022.
[15] Hongmin Cai, Zhixuan Zhou, Defu Yang, Guorong Wu, and Jiazhou Chen. Discovering brain network dysfunction in alzheimer’s
disease using brain hypergraph neural network. In International Conference on Medical Image Computing and Computer-Assisted
Intervention, 2023.
[16] Sebastian Pardo-Guerra, Vivek Kurien George, and Gabriel A Silva. On the graph isomorphism completeness of directed and
multidirected graphs. Mathematics, 13(2):228, 2025.
[17] Sebastian Pardo-Guerra, Vivek Kurien George, Vikash Morar, Joshua Roldan, and Gabriel Alex Silva. Extending undirected graph
techniques to directed graphs via category theory. Mathematics, 12(9):1357, 2024.
[18] Claude Berge. Hypergraphs: combinatorics of finite sets, volume 45. Elsevier, 1984.
[19] Alain Bretto. Hypergraph theory. An introduction. Mathematical Engineering. Cham: Springer, 1, 2013.
[20] Muhammad Akram, A Nagoor Gani, and A Borumand Saeid. Vague hypergraphs. Journal of Intelligent & Fuzzy Systems,
26(2):647–653, 2014.
[21] TM Nishad, Talal Ali Al-Hawary, and B Mohamed Harif. General fuzzy graphs. Ratio Mathematica, 47, 2023.
[22] Azriel Rosenfeld. Fuzzy graphs. In Fuzzy sets and their applications to cognitive and decision processes, pages 77–95. Elsevier,
1975.
[23] Said Broumi, Mohamed Talea, Assia Bakali, and Florentin Smarandache. Single valued neutrosophic graphs. Journal of New theory,
(10):86–101, 2016.
[24] Said Broumi, Mohamed Talea, Assia Bakali, Florentin Smarandache, and PK Kishore Kumar. Shortest path problem on single
valued neutrosophic graphs. In 2017 international symposium on networks, computers and communications (ISNCC), pages 1–6.
IEEE, 2017.
[25] Florentin Smarandache. Extension of HyperGraph to n-SuperHyperGraph and to Plithogenic n-SuperHyperGraph, and Extension
of HyperAlgebra to n-ary (Classical-/Neutro-/Anti-) HyperAlgebra. Infinite Study, 2020.
[26] Shouxian Zhu. Neutrosophic n-superhypernetwork: A new approach for evaluating short video communication effectiveness in
media convergence. Neutrosophic Sets and Systems, 85:1004–1017, 2025.
[27] Takaaki Fujita and Florentin Smarandache. A concise study of some superhypergraph classes. Neutrosophic Sets and Systems,
77:548–593, 2024.
التنزيلات
منشور
إصدار
القسم
الرخصة
الحقوق الفكرية (c) 2025 Takaaki Fujita
هذا العمل مرخص بموجب Creative Commons Attribution 4.0 International License.
All articles published in Abhath Journal of Basic and Applied Sciences (AJOBAS) are open-access and licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license allows users to freely share, copy, distribute, and adapt the work, provided that the original author(s) and source are properly credited.
