Search Results for author: Xinli Shi

Found 10 papers, 0 papers with code

ColorVein: Colorful Cancelable Vein Biometrics

no code implementations19 Apr 2025 Yifan Wang, Jie Gui, Xinli Shi, Linqing Gui, Yuan Yan Tang, James Tin-Yau Kwok

Unlike previous cancelable template generation schemes, ColorVein does not destroy the original biometric features and introduces additional color information to grayscale vein images.

Colorization

Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum

no code implementations17 Apr 2025 Yuan Zhou, Xinli Shi, Xuelong Li, Jiachen Zhong, Guanghui Wen, Jinde Cao

Employing DFL methods to solve such general optimization problems leads to the formulation of Decentralized Nonconvex Composite Federated Learning (DNCFL), a topic that remains largely underexplored.

Federated Learning

FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Data

no code implementations16 Apr 2025 Yuan Zhou, Jiachen Zhong, Xinli Shi, Guanghui Wen, Xinghuo Yu

To overcome these limitations, we propose a novel composite federated learning algorithm called \textbf{FedCanon}, designed to solve the optimization problems comprising a possibly non-convex loss function and a weakly convex, potentially non-smooth regularization term.

Computational Efficiency Federated Learning

Improving Fast Adversarial Training via Self-Knowledge Guidance

no code implementations26 Sep 2024 Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui, Xinli Shi, Yuan Cao, Yuan Yan Tang, James Tin-Yau Kwok

Based on the analysis, we mainly attribute the observed misalignment and disparity to the imbalanced optimization in FAT, which motivates us to optimize different training data adaptively to enhance robustness.

Adversarial Robustness Attribute

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective

no code implementations22 Jul 2024 Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong, Xinli Shi, Yuan Yan Tang, DaCheng Tao

However, FAT suffers from catastrophic overfitting, which leads to a performance drop compared with multi-step adversarial training.

CoLA

A Proximal Gradient Method With Probabilistic Multi-Gossip Communications for Decentralized Composite Optimization

no code implementations19 Dec 2023 Luyao Guo, Luqing Wang, Xinli Shi, Jinde Cao

In this paper, we propose a communication-efficient method MG-Skip with probabilistic local updates and multi-gossip communications for decentralized composite (smooth + nonsmooth) optimization, whose stepsize is independent of the number of local updates and the network topology.

Distributed Optimization

Decentralized Inexact Proximal Gradient Method With Network-Independent Stepsizes for Convex Composite Optimization

no code implementations7 Feb 2023 Luyao Guo, Xinli Shi, Jinde Cao, ZiHao Wang

The proposed algorithm uses uncoordinated network-independent constant stepsizes and only needs to approximately solve a sequence of proximal mappings, which is advantageous for solving decentralized composite optimization problems where the proximal mappings of the nonsmooth loss functions may not have analytical solutions.

BALPA: A Balanced Primal-Dual Algorithm for Nonsmooth Optimization with Application to Distributed Optimization

no code implementations6 Dec 2022 Luyao Guo, Jinde Cao, Xinli Shi, Shaofu Yang

In this paper, we propose a novel primal-dual proximal splitting algorithm (PD-PSA), named BALPA, for the composite optimization problem with equality constraints, where the loss function consists of a smooth term and a nonsmooth term composed with a linear mapping.

Distributed Optimization

DISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization

no code implementations5 Sep 2022 Luyao Guo, Xinli Shi, Shaofu Yang, Jinde Cao

In this paper, we propose a novel Dual Inexact Splitting Algorithm (DISA) for distributed convex composite optimization problems, where the local loss function consists of a smooth term and a possibly nonsmooth term composed with a linear mapping.

Cannot find the paper you are looking for? You can Submit a new open access paper.