Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Graph Neural Networks on Quantum Computers (2405.17060v1)

Published 27 May 2024 in quant-ph, cs.AI, and cs.LG

Abstract: Graph Neural Networks (GNNs) are powerful machine learning models that excel at analyzing structured data represented as graphs, demonstrating remarkable performance in applications like social network analysis and recommendation systems. However, classical GNNs face scalability challenges when dealing with large-scale graphs. This paper proposes frameworks for implementing GNNs on quantum computers to potentially address the challenges. We devise quantum algorithms corresponding to the three fundamental types of classical GNNs: Graph Convolutional Networks, Graph Attention Networks, and Message-Passing GNNs. A complexity analysis of our quantum implementation of the Simplified Graph Convolutional (SGC) Network shows potential quantum advantages over its classical counterpart, with significant improvements in time and space complexities. Our complexities can have trade-offs between the two: when optimizing for minimal circuit depth, our quantum SGC achieves logarithmic time complexity in the input sizes (albeit at the cost of linear space complexity). When optimizing for minimal qubit usage, the quantum SGC exhibits space complexity logarithmic in the input sizes, offering an exponential reduction compared to classical SGCs, while still maintaining better time complexity. These results suggest our Quantum GNN frameworks could efficiently process large-scale graphs. This work paves the way for implementing more advanced Graph Neural Network models on quantum computers, opening new possibilities in quantum machine learning for analyzing graph-structured data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. M. Zitnik, M. Agrawal, and J. Leskovec, Modeling polypharmacy side effects with graph convolutional networks, Bioinformatics  (2018).
  2. M. M. Bronstein, T. Cohen, and P. Veličković, Towards geometric deep learning, The Gradient  (2023).
  3. C. Joshi, Transformers are graph neural networks, The Gradient  (2020).
  4. C. K. Joshi, Recent advances in efficient and scalable graph neural networks, chaitjo.com  (2022).
  5. K. Kiningham, C. Re, and N. Alshurafa, Grip: a graph neural network accelerator architecture, in 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) (IEEE, 2020) pp. 570–583.
  6. A. Auten, M. Tomei, and R. Kumar, Hardware acceleration of graph neural networks, in 2020 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (IEEE, 2020) pp. 1–6.
  7. P. J. Coles, Seeking quantum advantage for neural networks, Nature Computational Science 1, 389 (2021).
  8. X. Gao, Z.-Y. Zhang, and L.-M. Duan, A quantum machine learning algorithm based on generative models, Science advances 4, eaat9004 (2018).
  9. P. Mernyei, K. Meichanetzidis, and I. I. Ceylan, Equivariant quantum graph circuits, in International Conference on Machine Learning (PMLR, 2022) pp. 15401–15420.
  10. T. N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, in Proc. of ICLR (2017).
  11. P. Veličković, Everything is connected: Graph neural networks, Current Opinion in Structural Biology 79, 102538 (2023).
  12. W. Hamilton, Z. Ying, and J. Leskovec, Inductive representation learning on large graphs, in NeurIPS (2017).
  13. G.-L. Long and Y. Sun, Efficient scheme for initializing a quantum register with an arbitrary superposed state, Phys. Rev. A 64, 014303 (2001).
  14. L. Grover and T. Rudolph, Creating superpositions that correspond to efficiently integrable probability distributions, arXiv:quant-ph/0208112  (2002).
  15. M. Plesch and Č. Brukner, Quantum-state preparation with universal gate decompositions, Phy. Rev. A 83, 032302 (2011).
  16. X.-M. Zhang, M.-H. Yung, and X. Yuan, Low-depth quantum state preparation, Phys. Rev. Res. 3, 043200 (2021).
  17. G. Rosenthal, Query and depth upper bounds for quantum unitaries via Grover search, arXiv:2111.07992  (2021).
  18. X.-M. Zhang, T. Li, and X. Yuan, Quantum state preparation with optimal circuit depth: Implementations and applications, Physical Review Letters 129, 230504 (2022).
  19. P. Yuan and S. Zhang, Optimal (controlled) quantum state preparation and improved unitary synthesis by quantum circuits with any number of ancillary qubits, Quantum 7, 956 (2023).
  20. X.-M. Zhang and X. Yuan, Circuit complexity of quantum access models for encoding classical data, npj Quantum Information 10, 42 (2024).
  21. N. Guo, K. Mitarai, and K. Fujii, Nonlinear transformation of complex amplitudes via quantum singular value transformation, arXiv preprint arXiv:2107.10764  (2021).
  22. J. Knörzer, D. Malz, and J. I. Cirac, Cross-platform verification in quantum networks, Phys. Rev. A 107, 062424 (2023).
  23. A. Luongo, Quantum algorithms for data analysis, Quantum Algorithms (2023).
  24. Y. Liao, M.-H. Hsieh, and C. Ferrie, Quantum optimization for training quantum neural networks, arXiv preprint arXiv:2103.17047  (2021).
  25. L. Friedrich and J. Maziero, Quantum neural network cost function concentration dependency on the parametrization expressivity, Scientific Reports 13, 1 (2023).
  26. S. Ragavan and V. Vaikuntanathan, Space-efficient and noise-robust quantum factoring (2024), arXiv:2310.00899 [quant-ph] .
  27. M. Defferrard, X. Bresson, and P. Vandergheynst, Convolutional neural networks on graphs with fast localized spectral filtering, in Proc. of NIPS (2016) pp. 3844–3852.
  28. C. Sünderhauf, E. Campbell, and J. Camps, Block-encoding structured matrices for data input in quantum computing, Quantum 8, 1226 (2024).
  29. L. Lin, Lecture notes on quantum algorithms for scientific computation, arXiv preprint arXiv:2201.08309  (2022).
  30. L. Gui-Lu, General quantum interference principle and duality computer, Communications in Theoretical Physics 45, 825 (2006).
  31. G. L. Long, Duality quantum computing and duality quantum information processing, International Journal of Theoretical Physics 50, 1305 (2011).
  32. A. M. Childs and N. Wiebe, Hamiltonian simulation using linear combinations of unitary operations, arXiv preprint arXiv:1202.5822  (2012).
  33. J. Landman, Quantum algorithms for unsupervised machine learning and neural networks, arXiv preprint arXiv:2111.03598  (2021).
  34. Y. Liao and C. Ferrie, Gpt on a quantum computer, arXiv preprint arXiv:2403.09418  (2024).
  35. D. Blakely, J. Lanchantin, and Y. Qi, Time and space complexity of graph convolutional networks, Accessed on: Dec 31, 2021 (2021).
  36. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (MIT Press, 2016).
  37. Y. Cao, G. G. Guerreschi, and A. Aspuru-Guzik, Quantum neuron: an elementary building block for machine learning on quantum computers, arXiv preprint arXiv:1711.11240  (2017).
  38. E. Torrontegui and J. J. García-Ripoll, Unitary quantum perceptron as efficient universal approximator, EPL (Europhys. Lett.) 125, 30004 (2019).
  39. M. Schuld, I. Sinayskiy, and F. Petruccione, How to simulate a perceptron using quantum circuits, Physics Letters A 379, 660 (2015).
  40. J. Zheng, Q. Gao, and Y. Lü, Quantum graph convolutional neural networks, arXiv preprint arXiv:2107.03257  (2021).
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now