Canh T. Dinh

Canh T. Dinh

Auto-generated profile, based on publicly available information

Canh T. Dinh

School of Computer Science, The University of Sydney, Sydney, NSW, Australia

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2020 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Closed access
CDCanh T. Dinh
Canh T. Dinh
NTNguyen H. Tran
Nguyen H. Tran
MNMinh N. H. Nguyen
Minh N. H. Nguyen
Choong Seon HongChoong Seon Hong
Choong Seon Hong
WBWei Bao
Wei Bao
VGVincent Gramoli
Vincent Gramoli
There is an increasing interest in a fast-growing machine learning technique called Federated Learning (FL), in which the model training is distributed over mobile user equipment (UEs), exploiting UEs' local computation and training data. Despite its advantages such as preserving data privacy, FL still has challenges of heterogeneity across UEs' data and physical resources. To address these challenges, we first propose FEDL, a FL algorithm which can handle heterogeneous UE data without further assumptions except strongly convex and smooth loss functions. We provide a convergence rate characterizing the trade-off between local computation rounds of each UE to update its local model and global communication rounds to update the FL global model. We then employ FEDL in wireless networks as a resource allocation optimization problem that captures the trade-off between FEDL convergence wall clock time and energy consumption of UEs with heterogeneous computing and power resources. Even though the wireless resource allocation problem of FEDL is non-convex, we exploit this problem's structure to decompose it into three sub-problems and analyze their closed-form solutions as well as insights into problem design. Finally, we empirically evaluate the convergence of FEDL with PyTorch experiments, and provide extensive numerical results for the wireless resource allocation sub-problems. Experimental results show that FEDL outperforms the vanilla FedAvg algorithm in terms of convergence rate and test accuracy in various settings.

7 December 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
CDCanh T. Dinh
Canh T. Dinh
TVTung T. Vu
Tung T. Vu
NTNguyen H. Tran
Nguyen H. Tran
MDMinh N. Dao
Minh N. Dao
Hongyu ZhangHongyu Zhang
Hongyu Zhang
Non-independent and identically distributed (non-IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL). Several approaches to handle non-IID data, such as personalized FL and federated multitask learning (FMTL), are of great interest to research communities. In this work, first, we formulate the FMTL problem using Laplacian regularization to explicitly leverage the relationships among the models of clients for multitask learning. Then, we introduce a new view of the FMTL problem, which, for the first time, shows that the formulated FMTL problem can be used for conventional FL and personalized FL. We also propose two algorithms and decentrali-zed () to solve the formulated FMTL problem in communication-centralized and decentralized schemes, respectively. Theoretically, we prove that the convergence rates of both algorithms achieve linear speedup for strongly convex and sublinear speedup of order $1/2$ for nonconvex objectives. Experimentally, we show that our algorithms outperform the conventional algorithm FedAvg, FedProx, SCAFFOLD, and AFL in FL settings, MOCHA in FMTL settings, as well as pFedMe and Per-FedAvg in personalized FL settings.

27 January 2022 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
CDCanh T. Dinh
Canh T. Dinh
NTNguyen H. Tran
Nguyen H. Tran
TNTuan Dung Nguyen
Tuan Dung Nguyen
WBWei Bao
Wei Bao
ABAmir Rezaei Balef
Amir Rezaei Balef
Albert ZomayaAlbert Zomaya
Albert Zomaya
There is growing interest in applying distributed machine learning to edge computing, forming federated edge learning. Federated edge learning faces non-i.i.d. and heterogeneous data, and the communication between edge workers, possibly through distant locations and with unstable wireless networks, is more costly than their local computational overhead. In this work, we propose DONE, a distributed approximate Newtontype algorithm with a fast convergence rate for communication efficient federated edge learning. First, with strongly convex and smooth loss functions, DONE approximates the Newton direction in a distributed manner using the classical Richardson iteration on each edge worker. Second, we prove that DONE has linear-quadratic convergence and analyze its communication complexities. Finally, the experimental results with non-i.i.d. and heterogeneous data show that DONE attains a comparable performance to Newtons method. Notably, DONE requires fewer communication iterations compared to distributed gradient descent and outperforms DANE, FEDL, and GIANT, state-of-the-art approaches, in the case of non-quadratic loss functions.


9 August 2021 in IEEE Communications Letters
Verified
Journal Article
Closed access
TNTuan Dung Nguyen
Tuan Dung Nguyen
ABAmir R. Balef
Amir R. Balef
CDCanh T. Dinh
Canh T. Dinh
NTNguyen H. Tran
Nguyen H. Tran
DNDuy T. Ngo
Duy T. Ngo
PVPhuong L. Vo
Phuong L. Vo
Transferring large models in federated learning (FL) networks is often hindered by clients’ limited bandwidth. We propose FedAA, an FL algorithm which achieves fast convergence by exploiting the regularized Anderson acceleration (AA) on the global level. First, we demonstrate that FL can benefit from acceleration methods in numerical analysis. Second, FedAA improves the convergence rate for quadratic losses and improves the empirical performance for smooth and strongly convex objectives, compared to FedAvg, an FL algorithm using gradient descent (GD) local updates. Experimental results demonstrate that employing AA can significantly improve the performance of FedAvg, even when the objective is non-convex.

15 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
TVTung T. Vu
Tung T. Vu
VTVan Chien Trinh
Van Chien Trinh
CDCanh T. Dinh
Canh T. Dinh
Hien Quoc NgoHien Quoc Ngo
Hien Quoc Ngo
MMMichail Matthaiou
Michail Matthaiou
For downlink massive multiple-input multiple-output (MIMO) operating in time-division duplex protocol, users can decode the signals effectively by only utilizing the channel statistics as long as channel hardening holds. However, in a reconfigurable intelligent surface (RIS)-assisted massive MIMO system, the propagation channels may be less hardened due to the extra random fluctuations of the effective channel gains. To address this issue, we propose a learning-based method that trains a neural network to learn a mapping between the received downlink signal and the effective channel gains. The proposed method does not require any downlink pilots and statistical information of interfering users. Numerical results show that, in terms of mean-square error of the channel estimation, our proposed learning-based method outperforms the state-of-the-art methods, especially when the light-of-sight (LoS) paths are dominated by non-LoS paths with a low level of channel hardening, e.g., in the cases of small numbers of RIS elements and/or base station antennas.