Qiaolun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qiaolun Zhang has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
- Massimo Tornatore
Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy
12 shared publications - Francesco Musumeci
Politecnico di Milano, Milan, Italy
6 shared publications - Alberto Gatto
Politecnico di Milano
4 shared publications - Jun Wu
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
4 shared publications - Xin Wang
College of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing, China
4 shared publications Massimo Tornatore
Politecnico di Milano Italy
3 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 44 (13) , 5464-5478
All-Optical Network Coding-Enabled Efficient Collective Communication Over OTN-Interconnected Inter-DC Networks
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 44 (13) , 5464-5478
All-Optical Network Coding-Enabled Efficient Collective Communication Over OTN-Interconnected Inter-DC Networks
- Open Access
- 27 March 2026
- Published by Springer Nature
- p. 117-124
Green, Resilient, and Secure Next-Generation Optical Networks
- 27 March 2026
- Published by Springer Nature
- p. 117-124
Open AccessGreen, Resilient, and Secure Next-Generation Optical Networks
- Open Access
Multi-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization
Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT.
Open AccessMulti-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization
Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Quantum Engineering
- Vol. 7, 4101113
Defending QKD Networks: Routing and Wavelength Assignment to Mitigate Physical-Layer Attacks
Quantum key distribution (QKD) supports secret key exchange to enable data exchange with guaranteed security but remains vulnerable to key exchange interruption caused by physical-layer threats, such as high-power jamming attacks. In particular, in a fiber-based QKD network equipped with optical switching capabilities, a high-power jamming signal injected into a single link can be optically switched and propagated to other links, resulting in the interruption of key exchange on multiple links. To address this challenge, we introduce a novel metric, the maximum number of affected requests (maxNAR), which quantifies the worst-case impact of a single physical-layer attack. Based on this, we investigate a new problem: Routing and Wavelength Assignment with Minimal Attack Radius (RWA-MAR). The objective of RWA-MAR is to assign routes and wavelengths to QKD requests in such a way that the maximum number of requests disrupted by any single physical-layer attack is minimized. We first formulate the problem using an integer linear programming (ILP) model to minimize maxNAR. Due to computational limitations of ILP, we develop a scalable deep reinforcement learning (DRL) solution that dynamically balances security (minimizing maxNAR) and resource efficiency. The DRL solution is designed to utilize key caches (defined as QKP) to minimize the maxNAR, as the QKP can save the keys for future use. Extensive simulations across diverse topologies and workloads show that our approach achieves a significant reduction in maxNAR (over 50%) compared to a baseline that performs RWA without considering the reduction of an attack impact. Meanwhile, our approach maintains reasonable resource efficiency in key delivery, marking a step toward robust and attack-aware QKD network design.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Quantum Engineering
- Vol. 7, 4101113
Open AccessDefending QKD Networks: Routing and Wavelength Assignment to Mitigate Physical-Layer Attacks
Quantum key distribution (QKD) supports secret key exchange to enable data exchange with guaranteed security but remains vulnerable to key exchange interruption caused by physical-layer threats, such as high-power jamming attacks. In particular, in a fiber-based QKD network equipped with optical switching capabilities, a high-power jamming signal injected into a single link can be optically switched and propagated to other links, resulting in the interruption of key exchange on multiple links. To address this challenge, we introduce a novel metric, the maximum number of affected requests (maxNAR), which quantifies the worst-case impact of a single physical-layer attack. Based on this, we investigate a new problem: Routing and Wavelength Assignment with Minimal Attack Radius (RWA-MAR). The objective of RWA-MAR is to assign routes and wavelengths to QKD requests in such a way that the maximum number of requests disrupted by any single physical-layer attack is minimized. We first formulate the problem using an integer linear programming (ILP) model to minimize maxNAR. Due to computational limitations of ILP, we develop a scalable deep reinforcement learning (DRL) solution that dynamically balances security (minimizing maxNAR) and resource efficiency. The DRL solution is designed to utilize key caches (defined as QKP) to minimize the maxNAR, as the QKP can save the keys for future use. Extensive simulations across diverse topologies and workloads show that our approach achieves a significant reduction in maxNAR (over 50%) compared to a baseline that performs RWA without considering the reduction of an attack impact. Meanwhile, our approach maintains reasonable resource efficiency in key delivery, marking a step toward robust and attack-aware QKD network design.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 44 (4) , 1342-1356
Flexible-Unit Deployment and Lightpath Provision Over 6G AI-RAN for Holographic Type Communications
HolographicType Communication (HTC) demands ultra-high bandwidth, substantial computing resources, ultra-low latency, and precise synchronization that exceed the capabilities of existing Radio Access Networks (RANs). These requirements exacerbate the inherent tradeoff between centralized baseband processing and fronthaul bandwidth efficiency, making traditional coarsegrained baseband function deployment and lightpath provision for unicast services insufficient to efficiently support HTC. In particular, 6G AI-RAN, by combining flexible spectrum and baseband processing allocation (i.e., by flexible-unit deployment), offers a promising solution for transmitting holograms and multisensory data. However, an efficient resource assignment in a 6G AI-RAN requires solving multiple sub-problems, involving Flexible Unit (FU) deployment and Holographic Routing and Spectrum Allocation (FHRSA). We formulate the FHRSA problem as an Integer Linear Programming (ILP) model and propose HoMa, a holographic viewpoint rotation prediction (HVRP)-based multi-agent deep-deterministic policy gradient (MADDPG) algorithm, to efficiently address it. HoMa employs a long-short-term memory (LSTM) network for HVRP, enabling accurate estimation of future resource demands. Leveraging these predictions, HoMa explicitly models inter-agent interactions and optimizes high-dimensional actions, achieving faster convergence, enhanced cooperation, and near-global optimal resource allocation. Simulation results demonstrate that the proposed HoMa algorithm significantly outperforms the benchmark algorithms in both small- and large-scale networks, achieving reductions of 20.29%, 38.96%, and 28.24% in multi-objective optimization cost, computational cost, and spectrum resource usage, respectively. Performance is closely aligned with the ILP model, validating its efficiency in resource allocation optimization.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 44 (4) , 1342-1356
Flexible-Unit Deployment and Lightpath Provision Over 6G AI-RAN for Holographic Type Communications
HolographicType Communication (HTC) demands ultra-high bandwidth, substantial computing resources, ultra-low latency, and precise synchronization that exceed the capabilities of existing Radio Access Networks (RANs). These requirements exacerbate the inherent tradeoff between centralized baseband processing and fronthaul bandwidth efficiency, making traditional coarsegrained baseband function deployment and lightpath provision for unicast services insufficient to efficiently support HTC. In particular, 6G AI-RAN, by combining flexible spectrum and baseband processing allocation (i.e., by flexible-unit deployment), offers a promising solution for transmitting holograms and multisensory data. However, an efficient resource assignment in a 6G AI-RAN requires solving multiple sub-problems, involving Flexible Unit (FU) deployment and Holographic Routing and Spectrum Allocation (FHRSA). We formulate the FHRSA problem as an Integer Linear Programming (ILP) model and propose HoMa, a holographic viewpoint rotation prediction (HVRP)-based multi-agent deep-deterministic policy gradient (MADDPG) algorithm, to efficiently address it. HoMa employs a long-short-term memory (LSTM) network for HVRP, enabling accurate estimation of future resource demands. Leveraging these predictions, HoMa explicitly models inter-agent interactions and optimizes high-dimensional actions, achieving faster convergence, enhanced cooperation, and near-global optimal resource allocation. Simulation results demonstrate that the proposed HoMa algorithm significantly outperforms the benchmark algorithms in both small- and large-scale networks, achieving reductions of 20.29%, 38.96%, and 28.24% in multi-objective optimization cost, computational cost, and spectrum resource usage, respectively. Performance is closely aligned with the ILP model, validating its efficiency in resource allocation optimization.
- Open Access
- 30 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 21-27
SCALE-CCL: A Scalable Collective Communication Library for Wide-Area Distributed Training
- 30 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 21-27
Open AccessSCALE-CCL: A Scalable Collective Communication Library for Wide-Area Distributed Training
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 69-72
Towards a wider optimisation of quantum communication infrastructure deployments
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 69-72
Open AccessTowards a wider optimisation of quantum communication infrastructure deployments
- Open Access
Routing and Wavelength Assignment with Minimal Attack Radius for QKD Networks
Quantum Key Distribution (QKD) can distribute keys with guaranteed security but remains susceptible to key exchange interruption due to physical-layer threats, such as high-power jamming attacks. To address this challenge, we first introduce a novel metric, namely Maximum Number of Affected Requests (maxNAR), to quantify the worst-case impact of a single physical-layer attack, and then we investigate a new problem of Routing and Wavelength Assignment with Minimal Attack Radius (RWA-MAR). We formulate the problem using an Integer Linear Programming (ILP) model and propose a scalable heuristic to efficiently minimize maxNAR. Our approach incorporates key caching through Quantum Key Pools (QKPs) to enhance resilience and optimize resource utilization. Moreover, we model the impact of different QKD network architectures, employing Optical Bypass (OB) for optical switching of quantum channels and Trusted Relay (TR) for secure key forwarding. Moreover, a tunable parameter is designed in the heuristic to guide the preference for OB or TR, offering enhanced adaptability and dynamic control in diverse network scenarios. Simulation results confirm that our method significantly outperforms the baseline in terms of security and scalability.
Open AccessRouting and Wavelength Assignment with Minimal Attack Radius for QKD Networks
Quantum Key Distribution (QKD) can distribute keys with guaranteed security but remains susceptible to key exchange interruption due to physical-layer threats, such as high-power jamming attacks. To address this challenge, we first introduce a novel metric, namely Maximum Number of Affected Requests (maxNAR), to quantify the worst-case impact of a single physical-layer attack, and then we investigate a new problem of Routing and Wavelength Assignment with Minimal Attack Radius (RWA-MAR). We formulate the problem using an Integer Linear Programming (ILP) model and propose a scalable heuristic to efficiently minimize maxNAR. Our approach incorporates key caching through Quantum Key Pools (QKPs) to enhance resilience and optimize resource utilization. Moreover, we model the impact of different QKD network architectures, employing Optical Bypass (OB) for optical switching of quantum channels and Trusted Relay (TR) for secure key forwarding. Moreover, a tunable parameter is designed in the heuristic to guide the preference for OB or TR, offering enhanced adaptability and dynamic control in diverse network scenarios. Simulation results confirm that our method significantly outperforms the baseline in terms of security and scalability.
- Open Access
- 15 July 2025
- Published by Elsevier in Optical Switching and Networking
- Vol. 57
Cost and power-consumption analysis for power profile monitoring with multiple monitors per link in optical networks
- 15 July 2025
- Published by Elsevier in Optical Switching and Networking
- Vol. 57
Open AccessCost and power-consumption analysis for power profile monitoring with multiple monitors per link in optical networks