58 citations · 372 across the 43 of their papers we have counts for
44 papers
FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
Junkang Liu, Fanhua Shang, Yuanyuan Liu +3
Although Federated Learning has been widely studied in recent years, there are still high overhead expenses in each communication round for large-scale models such as Vision Transf…
FedNSAM:Consistency of Local and Global Flatness for Federated Learning
Junkang Liu, Fanhua Shang, Yuxuan Tian +2
In federated learning (FL), multi-step local updates and data heterogeneity usually lead to sharper global minima, which degrades the performance of the global model. Popular FL al…
Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data
Junkang Liu, Fanhua Shang, Hongying Liu +3
Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key…
ILoRA: Federated Learning with Low-Rank Adaptation for Heterogeneous Client Aggregation
Junchao Zhou, Junkang Liu, Fanhua Shang
Federated Learning with Low-Rank Adaptation (LoRA) faces three critical challenges under client heterogeneity: (1) Initialization-Induced Instability due to random initialization m…
DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
Junkang Liu, Yuxuan Tian, Fanhua Shang +4
To prevent inference attacks in Federated Learning (FL) and reduce the leakage of sensitive information, Client-level Differentially Private Federated Learning (CL-DPFL) is widely…
FedMuon: Accelerating Federated Learning with Matrix Orthogonalization
Junkang Liu, Fanhua Shang, Junchao Zhou +3
The core bottleneck of Federated Learning (FL) lies in the communication rounds. That is, how to achieve more effective local updates is crucial for reducing communication rounds.…
FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
Junkang Liu, Fanhua Shang, Hongying Liu +5
AdamW has become one of the most effective optimizers for training large-scale models. We have also observed its effectiveness in the context of federated learning (FL). However, d…
Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
Zhijin Ge, Fanhua Shang, Hongying Liu +4
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high suc…
Boosting Adversarial Transferability by Achieving Flat Local Maxima
Zhijin Ge, Hongying Liu, Xiaosen Wang +2
Transfer-based attack adopts the adversarial examples generated on the surrogate model to attack various models, making it applicable in the physical world and attracting increasin…
Exploring Example Influence in Continual Learning
Qing Sun, Fan Lyu, Fanhua Shang +2
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new ta…
Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning
Hua Huang, Fanhua Shang, Yuanyuan Liu +1
Federated Learning (FL) has become an active and promising distributed machine learning paradigm. As a result of statistical heterogeneity, recent studies clearly show that the per…
Learned Interpretable Residual Extragradient ISTA for Sparse Coding
Lin Kong, Wei Sun, Fanhua Shang +2
Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have p…
Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
Qigong Sun, Xiufang Li, Fanhua Shang +4
The training of deep neural networks (DNNs) always requires intensive resources for both computation and data storage. Thus, DNNs cannot be efficiently applied to mobile phones and…
Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling
Hongying Liu, Peng Zhao, Zhubo Ruan +2
Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very impo…
MWQ: Multiscale Wavelet Quantized Neural Networks
Qigong Sun, Yan Ren, Licheng Jiao +3
Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardw…
Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization
Qigong Sun, Licheng Jiao, Yan Ren +3
Since model quantization helps to reduce the model size and computation latency, it has been successfully applied in many applications of mobile phones, embedded devices and smart…
Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks
Pengtao Xu, Jian Cao, Fanhua Shang +2
In order to deploy deep convolutional neural networks (CNNs) on resource-limited devices, many model pruning methods for filters and weights have been developed, while only a few t…
Differentially Private ADMM Algorithms for Machine Learning
Tao Xu, Fanhua Shang, Yuanyuan Liu +3
In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smoot…
Boosting Gradient for White-Box Adversarial Attacks
Hongying Liu, Zhenyu Zhou, Fanhua Shang +3
Deep neural networks (DNNs) are playing key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of…
A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-Resolution
Hongying Liu, Zhubo Ruan, Chaowei Fang +4
Spherical videos, also known as \ang{360} (panorama) videos, can be viewed with various virtual reality devices such as computers and head-mounted displays. They attract large amou…
Video Super Resolution Based on Deep Learning: A Comprehensive Survey
Hongying Liu, Zhubo Ruan, Peng Zhao +5
In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this…
Data Augmentation Imbalance For Imbalanced Attribute Classification
Yang Hu, Xiaying Bai, Pan Zhou +2
Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features fr…
A Unified Weight Learning and Low-Rank Regression Model for Robust Complex Error Modeling
Miaohua Zhang, Yongsheng Gao, Jun Zhou
One of the most important problems in regression-based error model is modeling the complex representation error caused by various corruptions and environment changes in images. For…
Deep Residual-Dense Lattice Network for Speech Enhancement
Mohammad Nikzad, Aaron Nicolson, Yongsheng Gao +3
Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enh…