Meilin Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Meilin Yang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Wenbo Ding
Tsinghua University
3 shared publications - Jian Xu
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
2 shared publications - Yang Liu
Hong Kong Polytechnic University, Hong Kong, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China
2 shared publications - Le Liang
School of Information Science and Engineering, Southeast University, Nanjing, China
1 shared publication - Shao-Lun Huang
Tsinghua University
1 shared publication - Tian Lan
George Washington University, Washington, DC, USA
1 shared publication
Latest Publications
- 24 December 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (3) , 1-18
Stabilizing and improving federated learning with highly non-iid data and client dropout
- 24 December 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (3) , 1-18
Stabilizing and improving federated learning with highly non-iid data and client dropout
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 35 (4) , 592-603
FedHAP: Federated Hashing With Global Prototypes for Cross-Silo Retrieval
Deep hashing has been widely applied in large-scale data retrieval due to its superior retrieval efficiency and low storage cost. However, data are often scattered in data silos with privacy concerns, so performing centralized data storage and retrieval is not always possible. Leveraging the approach of federated learning (FL) to perform deep hashing is a recent research trend. However, existing frameworks mostly rely on the aggregation of the local deep hashing models, which are trained by performing similarity learning with local skewed data only. Therefore, they cannot work well for non-IID clients in a real federated environment. To overcome these challenges, we propose a novel federated hashing framework that enables participating clients to jointly train a shared deep hashing model by leveraging the class-wise prototypical hash codes. Globally, sharing global prototypes with only one prototypical hash code per class assists in learning consistent code distributions across clients while minimizing the cost of communication and privacy. Locally, the use of the global prototypical hash codes are maximized by jointly training a discriminator network and the local hashing network. Extensive experiments on benchmark datasets are conducted to demonstrate that our method can significantly improve the performance of the deep hashing model in the federated environments with non-IID data distributions.
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 35 (4) , 592-603
FedHAP: Federated Hashing With Global Prototypes for Cross-Silo Retrieval
Deep hashing has been widely applied in large-scale data retrieval due to its superior retrieval efficiency and low storage cost. However, data are often scattered in data silos with privacy concerns, so performing centralized data storage and retrieval is not always possible. Leveraging the approach of federated learning (FL) to perform deep hashing is a recent research trend. However, existing frameworks mostly rely on the aggregation of the local deep hashing models, which are trained by performing similarity learning with local skewed data only. Therefore, they cannot work well for non-IID clients in a real federated environment. To overcome these challenges, we propose a novel federated hashing framework that enables participating clients to jointly train a shared deep hashing model by leveraging the class-wise prototypical hash codes. Globally, sharing global prototypes with only one prototypical hash code per class assists in learning consistent code distributions across clients while minimizing the cost of communication and privacy. Locally, the use of the global prototypical hash codes are maximized by jointly training a discriminator network and the local hashing network. Extensive experiments on benchmark datasets are conducted to demonstrate that our method can significantly improve the performance of the deep hashing model in the federated environments with non-IID data distributions.
- 18 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 4819-4831
SAFARI: Sparsity-Enabled Federated Learning With Limited and Unreliable Communications
Federated learning (FL) enables edge devices to collaboratively learn a model in a distributed fashion. Many existing researches have focused on improving communication efficiency of high-dimensional models and addressing bias caused by local updates. However, most FL algorithms are either based on reliable communications or assuming fixed and known unreliability characteristics. In practice, networks could suffer from dynamic channel conditions and non-deterministic disruptions, with time-varying and unknown characteristics. To this end, in this paper we propose a sparsity-enabled FL framework with both improved communication efficiency and bias reduction, termed as SAFARI. It makes use of similarity among client models to rectify and compensate for bias that results from unreliable communications. More precisely, sparse learning is implemented on local clients to mitigate communication overhead, while to cope with unreliable communications, a similarity-based compensation method is proposed to provide surrogates for missing model updates. With respect to sparse models, we analyze SAFARI under bounded dissimilarity. It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications. Implementations and evaluations on the CIFAR-10 dataset validate the effectiveness of SAFARI by showing that it can achieve the same convergence speed and accuracy as FedAvg with perfect communications, with up to 60% of the model weights being pruned and a high percentage of client updates missing in each round of model updates.
- 18 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 4819-4831
SAFARI: Sparsity-Enabled Federated Learning With Limited and Unreliable Communications
Federated learning (FL) enables edge devices to collaboratively learn a model in a distributed fashion. Many existing researches have focused on improving communication efficiency of high-dimensional models and addressing bias caused by local updates. However, most FL algorithms are either based on reliable communications or assuming fixed and known unreliability characteristics. In practice, networks could suffer from dynamic channel conditions and non-deterministic disruptions, with time-varying and unknown characteristics. To this end, in this paper we propose a sparsity-enabled FL framework with both improved communication efficiency and bias reduction, termed as SAFARI. It makes use of similarity among client models to rectify and compensate for bias that results from unreliable communications. More precisely, sparse learning is implemented on local clients to mitigate communication overhead, while to cope with unreliable communications, a similarity-based compensation method is proposed to provide surrogates for missing model updates. With respect to sparse models, we analyze SAFARI under bounded dissimilarity. It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications. Implementations and evaluations on the CIFAR-10 dataset validate the effectiveness of SAFARI by showing that it can achieve the same convergence speed and accuracy as FedAvg with perfect communications, with up to 60% of the model weights being pruned and a high percentage of client updates missing in each round of model updates.