Quantum Positional Encodings for Graph Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910480818241536 |
|---|---|
| author | Thabet, Slimane Djellabi, Mehdi Sokolov, Igor Kasture, Sachin Henry, Louis-Paul Henriet, Loïc |
| author_facet | Thabet, Slimane Djellabi, Mehdi Sokolov, Igor Kasture, Sachin Henry, Louis-Paul Henriet, Loïc |
| contents | In this work, we propose novel families of positional encodings tailored to graph neural networks obtained with quantum computers. These encodings leverage the long-range correlations inherent in quantum systems that arise from mapping the topology of a graph onto interactions between qubits in a quantum computer. Our inspiration stems from the recent advancements in quantum processing units, which offer computational capabilities beyond the reach of classical hardware. We prove that some of these quantum features are theoretically more expressive for certain graphs than the commonly used relative random walk probabilities. Empirically, we show that the performance of state-of-the-art models can be improved on standard benchmarks and large-scale datasets by computing tractable versions of quantum features. Our findings highlight the potential of leveraging quantum computing capabilities to enhance the performance of transformers in handling graph data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06547 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum Positional Encodings for Graph Neural Networks Thabet, Slimane Djellabi, Mehdi Sokolov, Igor Kasture, Sachin Henry, Louis-Paul Henriet, Loïc Quantum Physics In this work, we propose novel families of positional encodings tailored to graph neural networks obtained with quantum computers. These encodings leverage the long-range correlations inherent in quantum systems that arise from mapping the topology of a graph onto interactions between qubits in a quantum computer. Our inspiration stems from the recent advancements in quantum processing units, which offer computational capabilities beyond the reach of classical hardware. We prove that some of these quantum features are theoretically more expressive for certain graphs than the commonly used relative random walk probabilities. Empirically, we show that the performance of state-of-the-art models can be improved on standard benchmarks and large-scale datasets by computing tractable versions of quantum features. Our findings highlight the potential of leveraging quantum computing capabilities to enhance the performance of transformers in handling graph data. |
| title | Quantum Positional Encodings for Graph Neural Networks |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2406.06547 |