Zhihao Qu
YOU?
Author Swipe
View article: Prediction and verification of thin liquid film thickness on salt-deposited copper surface in an atmospheric hygrothermal environment
Prediction and verification of thin liquid film thickness on salt-deposited copper surface in an atmospheric hygrothermal environment Open
This study used laser spectroscopy testing technology and independently constructed a testing apparatus to achieve stable measurements of the adsorbed liquid film thickness on copper surfaces. The apparatus measurement accuracy reached 91.…
View article: Analytic Personalized Federated Meta-Learning
Analytic Personalized Federated Meta-Learning Open
Analytic Federated Learning (AFL) is an enhanced gradient-free federated learning (FL) paradigm designed to accelerate training by updating the global model in a single step with closed-form least-square (LS) solutions. However, the obtain…
View article: Enhance Learning Efficiency of Oblique Decision Tree via Feature Concatenation
Enhance Learning Efficiency of Oblique Decision Tree via Feature Concatenation Open
Oblique Decision Tree (ODT) separates the feature space by linear projections, as opposed to the conventional Decision Tree (DT) that forces axis-parallel splits. ODT has been proven to have a stronger representation ability than DT, as it…
View article: Reliability-Aware Hybrid Sfc Backup and Deployment in Edge Computing
Reliability-Aware Hybrid Sfc Backup and Deployment in Edge Computing Open
View article: Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning
Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning Open
This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that compre…
View article: Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning
Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning Open
This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that compre…
View article: Large Enhancement of Nonlinear Optical Response of Graphene Nanoribbonheterojunctions with Multiple Topological Interface States
Large Enhancement of Nonlinear Optical Response of Graphene Nanoribbonheterojunctions with Multiple Topological Interface States Open
View article: Topologically enhanced nonlinear optical response of graphene nanoribbon heterojunctions
Topologically enhanced nonlinear optical response of graphene nanoribbon heterojunctions Open
We study the nonlinear optical properties of heterojunctions made of graphene nanoribbons (GNRs) consisting of two segments with either the same or different topological properties. By utilizing a quantum mechanical approach that incorpora…
View article: Probiotics administration alleviates cognitive impairment and circadian rhythm disturbance induced by sleep deprivation
Probiotics administration alleviates cognitive impairment and circadian rhythm disturbance induced by sleep deprivation Open
Gut microbiome is indispensable for maintaining normal brain function. Specifically, gut microbiota plays a causal role in sleep deprivation (SD)-induced cognitive impairment. In this study, neurobehavioral effects of the Bifidobacterium b…
View article: Topologically enhanced nonlinear optical response of graphene nanoribbon heterojunctions
Topologically enhanced nonlinear optical response of graphene nanoribbon heterojunctions Open
We study the nonlinear optical properties of heterojunctions made of graphene nanoribbons (GNRs) consisting of two segments with either the same or different topological properties. By utilizing a quantum mechanical approach that incorpora…
View article: Network Coding Approaches for Distributed Computation over Lossy Wireless Networks
Network Coding Approaches for Distributed Computation over Lossy Wireless Networks Open
In wireless distributed computing systems, worker nodes connect to a master node wirelessly and perform large-scale computational tasks that are parallelized across them. However, the common phenomenon of straggling (i.e., worker nodes oft…
View article: A bidirectional DNN partition mechanism for efficient pipeline parallel training in cloud
A bidirectional DNN partition mechanism for efficient pipeline parallel training in cloud Open
Recently, deep neural networks (DNNs) have shown great promise in many fields while their parameter sizes are rapidly expanding. To break through the computation and memory limitation of a single machine, pipeline model parallelism is prop…
View article: A Bidirectional DNN Partition Mechanism for Efficient Pipeline Parallel Training in Cloud
A Bidirectional DNN Partition Mechanism for Efficient Pipeline Parallel Training in Cloud Open
Recently, deep neural networks (DNNs) have shown great promise in many fields while their parameter sizes are rapidly expanding. To break through the computation and memory limitation of a single machine, pipeline model parallelism is prop…
View article: Corrigendum: Pitting judgment model based on machine learning and feature optimization methods
Corrigendum: Pitting judgment model based on machine learning and feature optimization methods Open
Incorrect Funding In the published article, there was an error in the Funding statement. [No funding statement is included in published papers]. The correct Funding statement appears below.FUNDING[This work was supported by National Key R&…
View article: Anchor Sampling for Federated Learning with Partial Client Participation
Anchor Sampling for Federated Learning with Partial Client Participation Open
Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning, such as data heterogeneity. The lack of inactive clients' u…
View article: Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression Open
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds. …
View article: Formation and Evolution of the Corrosion Scales on Super 13Cr Stainless Steel in a Formate Completion Fluid With Aggressive Substances
Formation and Evolution of the Corrosion Scales on Super 13Cr Stainless Steel in a Formate Completion Fluid With Aggressive Substances Open
The formation and evolution of the corrosion scales on the super 13Cr stainless steel (SS) surface after exposure in a formate completion fluid with the presence of various aggressive substances was investigated. The results indicate that …
View article: Edge Learning for Distributed Big Data Analytics
Edge Learning for Distributed Big Data Analytics Open
Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques …
View article: From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization Open
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources. It is well acknowledged th…
View article: Pitting Judgment Model Based on Machine Learning and Feature Optimization Methods
Pitting Judgment Model Based on Machine Learning and Feature Optimization Methods Open
Pitting corrosion seriously harms the service life of oil field gathering and transportation pipelines, which is an important subject of corrosion prevention. In this study, we collected the corrosion data of pipeline steel immersion exper…
View article: On the Convergence of Quantized Parallel Restarted SGD for Serverless Learning
On the Convergence of Quantized Parallel Restarted SGD for Serverless Learning Open
With the growing data volume and the increasing concerns of data privacy, Stochastic Gradient Decent (SGD) based distributed training of deep neural network has been widely recognized as a promising approach. Compared with server-based arc…
View article: On the Convergence of Quantized Parallel Restarted SGD for Central Server Free Distributed Training
On the Convergence of Quantized Parallel Restarted SGD for Central Server Free Distributed Training Open
Communication is a crucial phase in the context of distributed training. Because parameter server (PS) frequently experiences network congestion, recent studies have found that training paradigms without a centralized server outperform the…
View article: Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning
Intermittent Pulling with Local Compensation for Communication-Efficient Federated Learning Open
Federated Learning is a powerful machine learning paradigm to cooperatively train a global model with highly distributed data. A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale…