Results 271 to 280 of about 2,708,601 (295)

RSGNN: A Model-agnostic Approach for Enhancing the Robustness of Signed Graph Neural Networks

The Web Conference, 2023
Signed graphs model complex relations using both positive and negative edges. Signed graph neural networks (SGNN) are powerful tools to analyze signed graphs. We address the vulnerability of SGNN to potential edge noise in the input graph. Our goal is to
Zeyu Zhang, Jiamou Liu, Xianda Zheng, Yifei Wang, Pengqian Han, Yupan Wang, Kaiqi Zhao, Zijian Zhang   +7 more
semanticscholar   +1 more source

Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics

AAAI Conference on Artificial Intelligence, 2023
Modeling continuous-time dynamics constitutes a foundational challenge, and uncovering inter-component correlations within complex systems holds promise for enhancing the efficacy of dynamic modeling.
Lanlan Chen, Kai Wu, Jian Lou, Jing Liu
semanticscholar   +1 more source

Fixed-Time Bipartite Containment Control of High-Order Multi-Agent Systems in the Signed Graph

IEEE Transactions on Circuits and Systems - II - Express Briefs, 2023
The fixed-time bipartite containment control for high-order multi-agent systems (MASs) with disturbances is discussed in directed signed graph. The proposed control algorithm guarantees that the trajectories of followers converge into the time-varying ...
Heng Zhan, Jie Wu, Xisheng Zhan, Tao Han, Huaicheng Yan   +4 more
semanticscholar   +1 more source

Signed Graph Neural Network with Latent Groups

Knowledge Discovery and Data Mining, 2021
Signed graph representation learning is an effective approach to analyze the complex patterns in real-world signed graphs with the co-existence of positive and negative links.
Haoxin Liu, Ziwei Zhang, Peng Cui, Yafeng Zhang, Qiang Cui, Jiashuo Liu, Wenwu Zhu   +6 more
semanticscholar   +1 more source

scSGL: kernelized signed graph learning for single-cell gene regulatory network inference

Bioinform., 2022
MOTIVATION Elucidating the topology of gene regulatory networks (GRNs) from large single-cell RNA sequencing (scRNAseq) datasets, while effectively capturing its inherent cell-cycle heterogeneity and dropouts, is currently one of the most pressing ...
Abdullah Karaaslanli, Satabdi Saha, Selin Aviyente, T. Maiti   +3 more
semanticscholar   +1 more source

Efficient Signed Graph Sampling via Balancing & Gershgorin Disc Perfect Alignment

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
A basic premise in graph signal processing (GSP) is that a graph encoding pairwise (anti-)correlations of the targeted signal as edge weights is leveraged for graph filtering. Existing fast graph sampling schemes are designed and tested only for positive
Chinthaka Dinesh, Gene Cheung, Saghar Bagheri, I. Bajić   +3 more
semanticscholar   +1 more source

SGFNNs: Signed Graph Filtering-based Neural Networks for Predicting Drug–Drug Interactions

J. Comput. Biol., 2022
Capturing comprehensive information about drug–drug interactions (DDIs) is one of the key tasks in public health and drug development. Recently, graph neural networks (GNNs) have received increasing attention in the drug discovery domain due to their ...
Ming Chen, Wei Jiang, Yi Pan, Jianhua Dai, Yunwen Lei, Chunyan Ji   +5 more
semanticscholar   +1 more source

H ∞ bipartite consensus of nonlinear multi-agent systems over a directed signed graph with a leader of non-zero input

International Journal of Control, 2021
This paper examines the bipartite tracking consensus for nonlinear multi-agents over a directed signed graph under bounded disturbances and a non-zero bounded input of the leader.
Amina Shams, M. Rehan, M. Tufail
semanticscholar   +1 more source

wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction

International Workshop on Complex Networks & Their Applications, 2021
Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains.
Marco Grassia, G. Mangioni
semanticscholar   +1 more source

WSGCN4SLP: Weighted Signed Graph Convolutional Network for Service Link Prediction

2021 IEEE International Conference on Web Services (ICWS), 2021
Learning network representations of Web services plays a critical role in the service ecosystem and facilitates many downstream tasks, e.g., service composition, service recommendation, service clustering, and service classification, etc.
Yong Xiao, Guosheng Kang, Jianxun Liu, Buqing Cao, Linghang Ding   +4 more
semanticscholar   +1 more source