Abstract
This paper introduces a novel structural approach to constructing associative knowledge graphs. These graphs are composed of many overlapping scenes, with each scene representing a specific set of objects. In the knowledge graph, each scene is represented as a complete subgraph associating scene objects. Knowledge graph nodes represent various objects present within the scenes. The same object can appear in multiple scenes. The recreation of the stored scenes from the knowledge graph occurs through association with a given context, which includes some of the objects stored in the graph. The memory capacity of the system is determined by the size of the graph and the density of its synaptic connections. Theoretical dependencies are derived to describe both the critical graph density and the memory capacity of scenes stored in such graphs. The critical graph density represents the maximum density at which it is possible to reproduce all elements of the scene without errors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amit, D.J., Gutfreund, H., Sompolinsky, H.: Storing infinite numbers of patterns in a spin-glass model of neural networks. Phys. Rev. Lett. 55, 1530 (1985). https://doi.org/10.1103/PhysRevLett.55.1530
Krotov, D., Hopfield, J.J.: Dense Associative Memory for Pattern Recognition (2016). http://arxiv.org/abs/1606.01164
Demircigil, M., Heusel, J., Löwe, M., Upgang, S., Vermet, F.: On a model of associative memory with huge storage capacity. J. Stat. Phys. 168(2), 288–299 (2017). https://doi.org/10.1007/s10955-017-1806-y
Ramsauer, H., et al.: Hopfield Networks is All You Need (2008). http://arxiv.org/abs/2008.02217
Schlag, I., Irie, K., Schmidhuber, J.: Linear Transformers are Secretly Fast Weight Programmers (2021). https://doi.org/10.48550/ARXIV.2102.11174
Vaswani, A., et al.: Attention is All You Need (2022). http://arxiv.org/abs/1706.03762. Accessed 21 Sept 2022
Arbib, M.A. (ed.): The Handbook of Brain Theory and Neural Networks, 1 Paperback edn. MIT Press, Cambridge (1998)
TensorFlow Transformer. https://www.tensorflow.org/text/tutorials/transformer. Accessed 11 Aug 2022
PyTorch Transformer. https://pytorch.org/docs/stable/generated/torch.nn.Transformer.html. Accessed 11 Aug 2022
Hawkins, J., George, D.: Hierarchical Temporal Memory: Concepts, Theory, and Terminology, Numenta Inc. Whitepaper (2006)
‘NuPIC PyTorch’. https://nupictorch.readthedocs.io/en/latest/. Accessed 11 Aug 2023
Ahmad, S., Scheinkman, L.: How Can We Be So Dense? The Benefits of Using Highly Sparse Representations (2023). http://arxiv.org/abs/1903.11257. Accessed 11 Aug 2023
Neo4J Graph Data Platform. https://neo4j.com/. Accessed 11 Aug 2023
Zhou, J., et al.: Graph Neural Networks: A Review of Methods and Applications (2018). https://doi.org/10.48550/ARXIV.1812.08434
Zhang, Z., Cui, P., Zhu, W.: Deep Learning on Graphs: A Survey (2018). http://arxiv.org/abs/1812.04202
Horzyk, A., Starzyk, J.A., Graham, J.: Integration of semantic and episodic memories. IEEE Trans. Neural Netw. Learn. Syst. 28(12), 3084–3095 (2017). https://doi.org/10.1109/TNNLS.2017.2728203
Horzyk, A.: How does generalization and creativity come into being in neural associative systems and how does it form human-like knowledge? Neurocomputing 144, 238–257 (2014). https://doi.org/10.1016/j.neucom.2014.04.046
Lin, T.Y., et al.: Microsoft COCO: Common Objects in Context. http://arxiv.org/abs/1405.0312. Accessed: 15 Jan 2023
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection (2019). https://doi.org/10.48550/ARXIV.1911.09070
Moore, B.E., Corso, J.J.: FiftyOne (2020). GitHub. https://github.com/voxel51/fiftyone
Structural Properties of Associative Knowledge Graphs (2023). https://github.com/PrzemyslawStok/Structural-Properties-of-Associative-Knowledge-Graphs.git. Accessed 11 Aug 2023
Fisher, R.A.: UCI Machine Learning Repository (1936). https://archive.ics.uci.edu/ml/datasets/Iris. Accessed 11 Aug 2023
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Starzyk, J.A., Stokłosa, P., Horzyk, A., Raif, P. (2024). Structural Properties of Associative Knowledge Graphs. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14450. Springer, Singapore. https://doi.org/10.1007/978-981-99-8070-3_25
Download citation
DOI: https://doi.org/10.1007/978-981-99-8070-3_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8069-7
Online ISBN: 978-981-99-8070-3
eBook Packages: Computer ScienceComputer Science (R0)