Rihuan Ke
Rihuan Ke
This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many exi...
A Method for Data Augmentation in Vertical Federated Learning Addressing Data Heterogeneity [0.03%]
一种针对垂直联邦学习数据异质性问题的数据增强方法
Yunpeng Xiao,Tingting Lv,Dengke Zhao et al.
Yunpeng Xiao et al.
Vertical federated learning (VFL) can aggregate data features from participating parties and is applicable to data collaboration in various fields. To address data heterogeneity in VFL, this article proposes a framework tailored for heterog...
Heterogeneous Demand-Aware Multi-Agent Communication Based on Role Representation [0.03%]
基于角色表示的异质需求感知的多智能体通信
Dongkun Huo,Huateng Zhang,Yixue Hao et al.
Dongkun Huo et al.
Efficient communication can help agents to overcome the limitations of partial observations on decision-making and enhance performance in collaborative multi-agent reinforcement learning (MARL). Researchers focus on constructing teammate mo...
MALFM-Captioner: A Multipath Alignment Learning for Image Captioning With Feature Mask [0.03%]
基于特征掩膜图像描述的多重路径对齐学习模型
Xiaobao Yang,Bohui Song,Yizhuo Dong et al.
Xiaobao Yang et al.
Diffusion-based image captioning models effectively mitigate the token dependency issue inherent in autoregressive methods. However, the noise introduced in diffusion methods weakens sentence information, resulting in insufficient ability o...
Recovering Reward Functions From Distributed Expert Demonstrations via Bi-Level Maximum-Likelihood Optimization [0.03%]
基于双层最大似然优化的分布式专家示教回报函数恢复算法
Guangyu Jiang,Shu Hong,Mahdi Imani et al.
Guangyu Jiang et al.
Inverse reinforcement learning (IRL) seeks to infer the latent reward function and the associated optimal policy from expert demonstrations. However, most current IRL methods assume centralized access to all trajectory data, which is imprac...
Fourier-Net+: Band-Limited Spatial Representation for Efficient Medical Image Registration [0.03%]
傅立叶网络+：用于高效医学图像配准的带限空间表示法
Xi Jia,Alexander Thorley,Alberto Gomez et al.
Xi Jia et al.
U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric image data, this process is, however, resource-intensiv...
Intrinsic Value-Aligned Policy Optimization for Offline-to-Online Reinforcement Learning [0.03%]
面向离线到在线强化学习的内在价值对齐策略优化方法
Tenglong Liu,Xin Xu,Xuhui Xie et al.
Tenglong Liu et al.
Offline-to-online reinforcement learning (O2O RL) enables agents to leverage offline pretrained policies and efficiently adapt to target environments through limited online interactions. However, during the transition from offline training ...
Toward Privacy Preservation in Federated Learning: A Framework Integrating Client-Side Shuffling and Model Compression [0.03%]
一种框架集成客户端洗牌和模型压缩的 federated learning 中保护隐私的方法
Jinguo Li,Ruyang Xiao,Le Yu et al.
Jinguo Li et al.
Federated learning (FL) enables multiple clients to train models on local data and collaboratively optimize a global model without sharing raw data. However, client heterogeneity, such as differences in data distributions and system capabil...
Data-Driven Output Feedback Control for Unknown Piecewise Affine Systems [0.03%]
基于数据的未知分段仿射系统的输出反馈控制
Kaijian Hu,Tao Liu
Kaijian Hu
This article investigates data-driven output feedback control of unknown piecewise affine (PWA) systems. The objective is to design controllers that exponentially stabilize PWA systems without requiring explicit subsystem models. A data-dep...
TSGNAS: A Topology- and Semantic-Guided Graph Neural Network Architecture Searcher [0.03%]
基于拓扑和语义的图神经网络架构搜索器
Kuijie Zhang,Shanchen Pang,Hongjuan Pei et al.
Kuijie Zhang et al.
Designing effective graph neural networks (GNNs) for diverse tasks requires substantial manual effort, especially when dealing with the intricate interplay between topological structures and semantic information in graph data. Existing auto...