Inflamed
发表于 2025-3-23 13:39:39
Key Substructure-Driven Backdoor Attacks on Graph Neural Networkscker-chosen target class key substructures, modifying few critical edges and nodes. Our approach across real datasets spanning diverse domains highlights its efficiency. The proposed methodology establishes a pioneering direction for refining backdoor attack techniques on GNNs.
无可争辩
发表于 2025-3-23 15:22:10
Missing Data Imputation via Neighbor Data Feature-Enriched Neural Ordinary Differential Equationsetwork is then employed to learn adjacent information of neighboring variables. The temporal information is captured by applying a gate recurrent unit module, thereby obtaining a spatiotemporal prior. The decoder introduces an ordinary differential equation module to generate a series of continuous
尊严
发表于 2025-3-23 19:05:28
http://reply.papertrans.cn/17/1677/167617/167617_13.png
间谍活动
发表于 2025-3-24 00:37:08
STGNA: Spatial-Temporal Graph Convolutional Networks with Node Level Attention for Shortwave Communiatial-temporal patterns of shortwave communications parameters, yielding to enhanced forecasting accuracy. Comprehensive experiments on a targeted dataset demonstrate that our approach significantly outperforms other baselines in forecasting accuracy.
innate
发表于 2025-3-24 05:37:45
Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Informormation aggregation with only 4 layers. Additionally, we demonstrate that VN-HGCN can serve as a versatile framework that can be seamlessly applied to other HGNN models, showcasing its generalizability. Empirical evaluations validate the effectiveness of VN-HGCN, and extensive experiments conducted
febrile
发表于 2025-3-24 08:20:32
http://reply.papertrans.cn/17/1677/167617/167617_16.png
enchant
发表于 2025-3-24 12:56:07
An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration of the reasoning results. Experimental results show that our scheme significantly progressed across multiple datasets, notably achieving an improvement of over 10% on the QALD10 dataset compared to both the best baseline and the fine-tuned state-of-the-art (SOTA) models.
ATP861
发表于 2025-3-24 17:42:30
http://reply.papertrans.cn/17/1677/167617/167617_18.png
Affirm
发表于 2025-3-24 22:39:48
http://reply.papertrans.cn/17/1677/167617/167617_19.png
HACK
发表于 2025-3-25 02:50:50
http://reply.papertrans.cn/17/1677/167617/167617_20.png