CLIP Graph Adaptor: A Dual-Graph Adapted Visual-Language Model for Weakly Supervised Semantic Segmentation [0.03%]
基于双图的CLIP模型适应方法：一种弱监督语义分割方法
Jia Zhang,Bo Peng,Xi Wu et al.
Jia Zhang et al.
Recent advancements in weakly supervised semantic segmentation (WSSS) have shown promise by using the contrastive language-image pretraining (CLIP) model to generate pseudo-labels. However, directly applying the CLIP model without consideri...
Node Classification in GNNs: Impact of Neighborhood Label Distribution on Homophily and Heterophily [0.03%]
图神经网络中节点分类：邻居标签分布对同质性和异质性的影响
Zhili Zhao,Li Wan,Xupeng Liu et al.
Zhili Zhao et al.
In node classification, traditional graph neural networks (GNNs) typically assume implicit homophily, indicating that intraclass nodes are likely connected. However, real-world graphs frequently exhibit heterophily, in which interclass node...
FedSKD: Aggregation-Free Model-Heterogeneous Federated Learning via Multidimensional Similarity Knowledge Distillation for Medical Image Classification [0.03%]
基于多维相似性知识蒸馏的模型异构联邦学习FedSKD用于医学图像分类
Ziqiao Weng,Weidong Cai,Bo Zhou
Ziqiao Weng
Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) enables clients to train personalized models with heterogeneous architectures, but existing methods m...
Ruinan Jin,Minghui Chen,Qiong Zhang et al.
Ruinan Jin et al.
The advent of federated learning (FL) has revolutionized the way distributed systems handle collaborative model training while preserving user privacy. Recently, federated unlearning (FU) has emerged to address demands for the "right to be ...
Systematic Abductive Reasoning via Diverse Relation Representations in Vector-Symbolic Architecture [0.03%]
基于向量符号架构的多样关系表示的系统 abduction 推理
Zhong-Hua Sun,Ru-Yuan Zhang,Zonglei Zhen et al.
Zhong-Hua Sun et al.
In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attribute and relatio...
Binbin Huang,Teng Bao,Feiyi Chen et al.
Binbin Huang et al.
The growth of large models demands multinode cooperation during training and inference processes. The computing node failures can interrupt these processes, subsequently causing information loss and prolonging the execution time. To reduce ...
Multiscale Graph Redefining: Correlation-Based Multiscale Graph Clustering Network for Human Motion Prediction [0.03%]
相关性多尺度图重定义：用于人体运动预测的多尺度图聚类网络
Jianqi Zhong,Junyu Shi,Wenming Cao
Jianqi Zhong
Graph Convolutional Networks (GCNs) have exhibited considerable promise in 3-D skeleton-based human motion prediction. Based on the intuitive observation that human motion can be delineated through the physical interconnections among human ...
A Fully Data-Driven Value Iteration for Stochastic LQR: Convergence, Robustness, and Stability [0.03%]
完全基于数据的随机LQR值迭代：收敛性、鲁棒性和稳定性
Leilei Cui,Zhong-Ping Jiang,Petter N Kolm et al.
Leilei Cui et al.
Unlike traditional model-based reinforcement learning (RL) approaches that estimate system parameters from data, nonmodel-based data-driven control learns the optimal policy directly from input-state data without any intermediate model iden...
Scalable and Efficient Deep Reinforcement Learning-Based Model Checker for Computation Tree Logic [0.03%]
一种基于深度强化学习的可扩展高效CTL属性检测方法
Ghalya Alwhishi,Jamal Bentahar,Amine Andam et al.
Ghalya Alwhishi et al.
Formal verification using temporal logics such as computation tree logic (CTL) is essential for validating safety and correctness in complex systems. However, traditional model-checking techniques face severe scalability limitations due to ...
Spectral-Spatial-Temporal Kolmogorov-Arnold Network for Hyperspectral Change Detection [0.03%]
基于谱空时的Kolmogorov-Arnold网络的高光谱变化检测方法
Puhong Duan,Wenxuan Wang,Xudong Kang et al.
Puhong Duan et al.
Hyperspectral change detection (HCD) aims to recognize altered areas between hyperspectral images (HSIs) captured at different times, which is one of the crucial research areas in remote sensing. In recent years, convolutional neural networ...