Aug 2026· Proceedings of the 3rd ACM SIGCOMM Workshop on Quantum Networks and Distributed Quantum Computing· pp. 7-12· 0 citations· 22 references
TL;DR
π-DQML is presented, a simulation-based framework for studying distributed QML under QGT-induced noise and failures, which models the state-of-the-art QGT protocol and its induced noise/failure, and supports efficient noise/failure-aware distributed QML training through a hybrid differentiation method.
Abstract
Quantum machine learning (QML) offers a promising approach to learning complex, high-dimensional data distributions. However, scaling QML beyond a single quantum machine requires distributed quantum computing, which introduces additional noise and link failures through quantum communication protocols such as quantum gate teleportation (QGT). In this paper, we present ϵ-DQML, a simulation-based framework for studying distributed QML under QGT-induced noise and failures. ϵ-DQML models the state-of-the-art QGT protocol and its induced noise/failure, and supports efficient noise/failure-aware distributed QML training through a hybrid differentiation method. Preliminary studies on contrastive language-image pretraining and network traffic classification show that the impact of QGT-induced noise is task- and noise-level-dependent, motivating further study on noise/failure-aware distributed QML system design.
Quantum machine learning (QML) is an emerging research area that combines quantum computing with machine learning to exploit quantum superposition, entanglement, interference, and high-dimensional Hilbert-space representations. This paper presents a concise survey of QML models and algorithms for near-term noisy interm...
Ton That Tam Dinh, Manh Cuong Ho, Ayalneh Bitew Wondmagegn et al.· International Conference on...· 0 citations
Results demonstrate that a trainable quantum receiver can recover task-relevant semantic information from noise-distorted quantum states and maintain high classification performance, highlighting a distinction between physical-state recovery and semantic-feature recovery.
Melek Krichen, Nikhitha Nunavath, R. Bassoli et al.· 0 citations
Current research provides an overview of important QML algorithms, such as Quantum Support Vector Machines (QSVM), Quantum Neural Networks (QNN), Variational Quantum Eigensolvers (VQE), Quantum Approximate Optimization Algorithm (QAOA), and hybrid quantumclassical computing techniques, which have recently become more p...
J. Chen· Recent Research Reviews Jour...· 0 citations
This work introduces an adaptive relational learning framework for multi-instance quantum data that accesses pairwise and higher-order relations and opens routes to sensing and quantum-data applications where adaptive photonic QML can access relational features that are costly to recover with non-adaptive, measure-firs...
Marcin Jastrzębski, Yu Shang, Raj B. Patel et al.· 0 citations
This work forms a Markov Decision Process for the problem and uses double deep Q-networks with Message Passing Neural Networks, experience replay buffers, and curriculum training to obtain policies, indicating a promising method for interpretable policy extraction for large quantum networks, where direct training becom...
L. Rode, Sumeet Khatri, Supartha Podder· 0 citations
Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality. Statistical learning offers new possibilities in this regime through neural network protocols and classical shadows, while both methods have limitations: the former suffers from incompatible dataset construction rules, resul...
Yuxuan Du, Yi-Bo Yang, Tongliang Liu et al.· IEEE Transactions on Pattern...· 10 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
