Why Empirical Risk Minimization Performs Well for Open Set Domain Adaptation: A Theoretical Analysis From Causal View [0.03%]
从因果视角看为什么经验风险最小化在开放集领域适应中表现良好：理论分析
Huaming Du,Yaling Liu,Cancan Feng et al.
Huaming Du et al.
Open set domain adaptation (OSDA) faces two critical challenges: the emergence of unknown classes in the target domain and changes in observed distributions across domains. Although numerous studies have proposed advanced algorithms, recent...
Online Value Iteration for Unknown Nonlinear Multiagent Systems: A Model-Decoupled Encoding-Decoding Mechanism [0.03%]
未知非线性多智能体系统的在线值迭代：一种模型解耦的编解码机制
Tong Zhang,Yiyan Han,Le You et al.
Tong Zhang et al.
In practice, optimal consensus control for multiagent systems (MASs) is strictly constrained by limited communication bandwidth. Therefore, dynamic encoding-decoding mechanisms are designed to address this issue. However, unknown nonlinear ...
Hyo-Seok Hwang,Jaewon Kim,Junhee Seok
Hyo-Seok Hwang
Learning expressive and multimodal policies is essential for solving complex continuous control tasks. However, most reinforcement learning (RL) algorithms rely on unimodal or factorized Gaussian policies, limiting their representational fl...
Dynamic-n-Static Multiplex Graph Representation Learning for Improved Link Prediction [0.03%]
基于动态和静态复用图表示学习的改进链接预测方法
Jia Yu,Mengjun Ding,Weiqiang Sun
Jia Yu
Social systems often involve multiple types of relations, each exhibiting distinct temporal characteristics. Such systems can be modeled as temporal multiplex graphs in which each graph layer represents one type of relation. In this article...
Benefiting From OOD Samples in Open-Set Semi-Supervised Object Detection [0.03%]
利用开集半监督目标检测中的OOD样本受益
Yiqi Zou,Kuo Wang,Jichang Li et al.
Yiqi Zou et al.
Open-set semi-supervised object detection (OSSOD) is an emerging research area that relaxes the assumption of closed-set in semi-supervised object detection (SSOD), allowing unlabeled data to contain both in-distribution (ID) and out-of-dis...
Enhancing Generative Models for Modality Imputation of 3-D MRIs via Consistency-Aware Refinement and Super-Resolution Guidance [0.03%]
基于一致性感知精炼和超分辨率引导的模态插补生成模型增强方法
Zhiyun Song,Xin Wang,Honglin Xiong et al.
Zhiyun Song et al.
Reconstructing missing modalities of magnetic resonance images (MRIs) is a significant challenge in the medical imaging field. Current generative approaches such as generative adversarial networks (GANs) and diffusion models (DFs) have show...
A Real-Time Offset-Free Neural Network MPC Framework for Aeroengine Control on Embedded Systems [0.03%]
基于嵌入式系统的实时无偏移神经网络模型预测航空发动机控制框架
Wen-Tao Li,Si-Xin Wen,Xue-Fang Wang et al.
Wen-Tao Li et al.
Model predictive control (MPC) for aeroengines requires accurate prediction of complex nonlinear dynamics, which is challenging to achieve using traditional modeling approaches. While neural networks (NNs) offer strong nonlinear approximati...
Geometry-Aware Line Graph Transformer Pretraining for Molecular Property Prediction [0.03%]
基于几何感知的线图Transformer预训练分子性质预测模型
Peizhen Bai,Xianyuan Liu,Wenrui Fan et al.
Peizhen Bai et al.
Molecular property prediction with deep learning approaches has gained much attention over the past years. Due to the scarcity of labeled molecules, there has been growing interest in self-supervised learning (SSL) methods that learn genera...
Escaping Stability-Plasticity Dilemma in Online Continual Learning for Motion Forecasting via Synergetic Memory Rehearsal [0.03%]
基于协同记忆重演的在线连续学习稳定性和 plasticity dilemma 解决方法在运动预测中的应用研究
Yunlong Lin,Chao Lu,Tongshuai Wu et al.
Yunlong Lin et al.
Deep neural networks (DNNs) have achieved remarkable success in intelligent systems such as autonomous vehicles and robots. However, most DNN-based methods suffer from catastrophic forgetting, where the DNN may fail to maintain its performa...
From Stochastic Conjugate Gradient to Stochastic Second-Order Optimization, Driven by Conjugate Coefficient With Second-Order Information [0.03%]
从随机共轭梯度到带二阶信息的随机二阶优化方法
Zhuang Yang
Zhuang Yang
Conjugate gradient (CG) and second-order information (SOI) receive increasing interest due to their crucial role in improving stochastic first-order (SFO) algorithms for solving machine learning problems. Although a variety of stochastic CG...