Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 31 min ago
PreprintarXiv licencearXiv

Graph Neural Post-selection for Quantum Error Correction

  • Conor Carty
  • Tamas Noszko
  • Joschka Roffe
  • Roberto Bondesan
Open at sourcePDFDOICite

Abstract

Post-selection improves the logical reliability of quantum computation by rejecting shots which are likely to result in logical failure. We introduce graph neural networks that predict decoder failure without additional decoder executions, using only syndromes, and for high-rate quantum low-density parity-check (qLDPC) codes, existing belief-propagation posteriors. We evaluate rotated surface and bivariate bicycle (BB) code memories under uniform depolarising circuit-level noise. Retaining 90% of shots gives approximately 3700x and 740x reductions in logical error rates for [[72,12,6]] and [[144,12,12]] BB codes at realistic physical error rates. For the distance 5 surface code at physical noise p=0.003, our neural post-selector achieves logical error suppression comparable to the leading complementary gap method without running the decoder.

Related

  1. Scalable neural decoders for practical real-time quantum error correction
    Changwon Lee, Tak Hur, Daniel K. Park
    npj Quantum InformationPeer-reviewedCC BY 4.0Quantum physics & quantum informationCrossref
  2. Bosonic quantum error correction with microwave cavities for quantum repeaters
    S. Siddardha Chelluri, Sanchar Sharma, Frank Schmidt +2
    Physical Review APeer-reviewedLicence not statedFull textQuantum physics & quantum informationHAL
  3. Error-Correction Transitions in Finite-Depth Quantum Channels
    Arman Sauliere, Guglielmo Lami, Pedro Ribeiro +2
    Physical Review LettersPeer-reviewedLicence not statedGeneral physicsHAL
  4. Quantum Error Correction and the Limits of Quantum Metrology
    Zhuoran Bao, Daniel F. V. James
    arXivPreprintCC0Full textOptics & photonicsQuantum physics & quantum informationarXiv
  5. High-Rank Encoding Can Improve Approximate Quantum Error Correction
    Bikun Li, Liang Jiang
    arXivPreprintCC BY 4.0Full textMathematical physicsQuantum physics & quantum informationarXiv

Cite

BibTeXRIS
BibTeX
@misc{carty2026graph,
  title = {{Graph Neural Post-selection for Quantum Error Correction}},
  author = {Conor Carty and Tamas Noszko and Joschka Roffe and Roberto Bondesan},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.00504},
  eprint = {2610.00504},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.00504},
}
RIS
TY  - UNPB
TI  - Graph Neural Post-selection for Quantum Error Correction
AU  - Conor Carty
AU  - Tamas Noszko
AU  - Joschka Roffe
AU  - Roberto Bondesan
PY  - 2026
DA  - 2026/10/01
PB  - arXiv
DO  - 10.48550/arxiv.2610.00504
UR  - https://arxiv.org/abs/2610.00504
AB  - Post-selection improves the logical reliability of quantum computation by rejecting shots which are likely to result in logical failure. We introduce graph neural networks that predict decoder failure without additional decoder executions, using only syndromes, and for high-rate quantum low-density parity-check (qLDPC) codes, existing belief-propagation posteriors. We evaluate rotated surface and bivariate bicycle (BB) code memories under uniform depolarising circuit-level noise. Retaining 90% of shots gives approximately 3700x and 740x reductions in logical error rates for [[72,12,6]] and [[144,12,12]] BB codes at realistic physical error rates. For the distance 5 surface code at physical noise p=0.003, our neural post-selector achieves logical error suppression comparable to the leading complementary gap method without running the decoder.
ER  -