Filters








2,463 Hits in 7.4 sec

RRGCCAN: Re-ranking via Graph Convolution Channel Attention Network for Person Re-Identification

Xiaoqiang Chen, Ling Zheng, Chong Zhao, Qicong Wang, Maozhen Li
2020 IEEE Access  
INDEX TERMS Person re-identification, graph convolution network, attention mechanism, context information.  ...  In this paper, we incorporate graph models on feature subsets resorting to the initial ranking by adopting the integration of the attention mechanism into graph convolution network.  ...  As a result, the subgraphs are learned with edges re-weighted by new feature similarities.  ... 
doi:10.1109/access.2020.3009653 fatcat:qjiss6dbtfboxnd6adroyndjji

GCN-Based Linkage Prediction for Face Clustering on Imbalanced Datasets: An Empirical Study [article]

Huafeng Yang, Xingjian Chen, Fangyi Zhang, Guangyue Hei, Yunjie Wang, Rong Du
2021 arXiv   pre-print
However, rare attention has been paid to GCN-based clustering on imbalanced data.  ...  The problem of imbalanced linkage labels is similar to that in image classification task, but the latter is a particular problem in GCN-based clustering via linkage prediction.  ...  ; • typical re-sampling and re-weighting approaches for the imbalance problem in image classification are transferred to tackle the label imbalance problem in GCNbased linkage prediction task, with evaluations  ... 
arXiv:2107.02477v2 fatcat:p6thznegwjfslitl5zvyx45cna

GNNExplainer: Generating Explanations for Graph Neural Networks

Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec
2019 Advances in Neural Information Processing Systems  
Here we propose GnnExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.  ...  Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
pmid:32265580 pmcid:PMC7138248 fatcat:fde4qszuyzg35oerrwnr7ettgm

GNNExplainer: Generating Explanations for Graph Neural Networks [article]

Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec
2019 arXiv   pre-print
Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.  ...  Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:1903.03894v4 fatcat:igx34dpky5hsbi2q53zxld3d64

Estimating latent positions of actors using Neural Networks in R with GCN4R [article]

Joshua Levy, Carly A Bobak, Brock Christensen, Louis J Vaickus, A. James O'Malley
2020 bioRxiv   pre-print
While statistical and machine learning prediction models generally assume independence between actors, network-based statistical methods for social network data allow for dyadic dependence between actors  ...  Here, we introduce GCN4R, an R library for fitting graph neural networks on independent networks to aggregate actor covariate information to yield meaningful embeddings for a variety of network-based tasks  ...  seek to derive an importance score for each node based on centrality measures that are weighted by the learned attention weights.  ... 
doi:10.1101/2020.11.02.364935 fatcat:qkiyeymuxjalbhx6blekhzpg3a

Vulnerable Brain Networks Associated with Risk for Alzheimer's Disease [article]

Ali Mahzarnia, Jacques A Stout, Robert J Anderson, Hae Sol Moon, Zay Yar Han, Kate Beck, Jeffrey N Browndyke, David B. Dunson, Kim G Johnson, Richard J O'Brien, Alexandra Badea
2022 bioRxiv   pre-print
Our sparse regression based predictive models revealed vulnerable networks associated with known risk factors.  ...  Our predictive modeling approaches for AD risk factors represent a stepping stone towards single subject prediction, based on distances from normative graphs.  ...  As expected age prediction involved extensive brain networks, and the large subgraph was associated with the highest weight. A large weight was also found for the accumbens.  ... 
doi:10.1101/2022.06.15.496331 fatcat:z3vybacagjfszhr5tv6vjmbpvy

Hierarchical Graph Transformer Based Deep Learning Model for Large-Scale Multi-Label Text Classification

Jibing Gong, Mingsheng Liu, Hongyuan Ma, Zhiyong Teng, Qi Teng, Hekai Zhang, Hekai Zhang, Linfeng Du, Shuai Chen, Md Zakirul Alam Bhuiyan, Jianhua Li
2020 IEEE Access  
For more information, see http://creativecommons.org/licenses/by/4.0/ 30885 J. Gong et al.: Hierarchical Graph Transformer-Based Deep Learning Model for Large-Scale Multi-Label Text Classification  ...  In this paper, we propose a novel Hierarchical Graph Transformer based deep learning model for large-scale multi-label text classification.  ...  Recently, graph-based architecture has attracted increasing research attention for use in social networks and recommendation systems [8] - [10] .  ... 
doi:10.1109/access.2020.2972751 fatcat:23yky5bbhzgfnlygi3hc3whk7a

Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks [article]

Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury, Chandan K. Reddy
2021 arXiv   pre-print
We first pre-train our model in a self-supervised manner by introducing higher-order semantic associations and masking nodes, and then fine-tune our model for a specific link prediction task.  ...  In practice, however, downstream tasks such as link prediction require specific contextual information that can be extracted from the subgraphs related to the nodes provided as input to the task.  ...  ACKNOWLEDGMENTS This work was supported in part by the US National Science Foundation grant IIS-1838730, Amazon AWS cloud computing credits, and Pacific Northwest National Laboratory under DOE-VA-21831018920  ... 
arXiv:2007.11192v3 fatcat:k2em3gretzd7fkdjrrvyi5k5pm

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text [article]

Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William W. Cohen
2018 arXiv   pre-print
Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone.  ...  Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations.  ...  Acknowledgments Bhuwan Dhingra is supported by NSF under grants CCF-1414030 and IIS-1250956 and by grants from Google.  ... 
arXiv:1809.00782v1 fatcat:jjb2vfwesjdi5obd4rtj7zhs64

Link mining

Lise Getoor, Christopher P. Diehl
2005 SIGKDD Explorations  
Commonly addressed link mining tasks include object ranking, group detection, collective classification, link prediction and subgraph discovery.  ...  Examples of homogeneous networks include single mode social networks, such as people connected by friendship links, or the WWW, a collection of linked web pages.  ...  Acknowledgments Thanks to the students in the LINQs group at UMD, especially Indrajit Bhattacharya, Mustafa Bilgic, and Prithviraj Sen for their input.  ... 
doi:10.1145/1117454.1117456 fatcat:z33bv3nf3rac5o3t43poebum7i

Link Prediction using Graph Neural Networks for Master Data Management [article]

Balaji Ganesan, Srinivas Parkala, Neeraj R Singh, Sumit Bhatia, Gayatri Mishra, Matheen Ahmed Pasha, Hima Patel, Somashekar Naganna
2020 arXiv   pre-print
We introduce novel methods for anonymizing data, model training, explainability and verification for Link Prediction in Master Data Management, and discuss our results.  ...  Predicting links between people using Graph Neural Networks requires careful ethical and privacy considerations than in domains where GNNs have typically been applied so far.  ...  In recent years, Graph Neural Networks (GNN) are being used for link prediction and node classification tasks.  ... 
arXiv:2003.04732v2 fatcat:qfak6f4265gerl7yvj36nbl444

Learning about Learning: Human Brain Sub-Network Biomarkers in fMRI Data [article]

Petko Bogdanov, Nazli Dereli, Danielle S. Bassett, Scott T. Grafton, Ambuj K. Singh
2014 arXiv   pre-print
We employ a principled approach for the discovery of significant subgraphs of functional connectivity, induced by brain activity (measured via fMRI imaging) while subjects perform a motor learning task  ...  In contrast, we seek to uncover subgraphs of functional connectivity that predict or drive individual differences in sensorimotor learning across subjects.  ...  Using data from an fMRI study coupled with performance (rate of learning within a session), we demonstrate the existence of subgraphs whose edge states are discriminative and thus can predict the rate  ... 
arXiv:1407.5590v1 fatcat:fkan54mzmbha7bkrn4e54wbzy4

Improving the Robustness of GraphSAINT via Stability Training

Yuying Wang, Huixuan Chi, Qinfen Hao
2021 ParadigmPlus  
For example, when Graph SAmpling based INductive learning meThod (GraphSAINT) is applied for the link prediction task, it may not converge in training with a probability range from 0.1 to 0.4.  ...  Graph Neural Networks (GNNs) field has a dramatic development nowadays due to the strong representation capabilities for data in non-Euclidean space, such as graph data.  ...  Acknowledgments This research was funded by the Fifth Innovative Project of State Key Laboratory of Computer Architecture (ICT, CAS) under Grant No. CARCH 5403.  ... 
doi:10.55969/paradigmplus.v2n3a1 fatcat:5tyd3ngcs5epxlha7ibegshcqq

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William Cohen
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone.  ...  Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations.  ...  Acknowledgments Bhuwan Dhingra is supported by NSF under grants CCF-1414030 and IIS-1250956 and by grants from Google.  ... 
doi:10.18653/v1/d18-1455 dblp:conf/emnlp/SunDZMSC18 fatcat:v33cv2wnfjbqnfuokptvv5xkxu

Learn molecular representations from large-scale unlabeled molecules for drug discovery [article]

Pengyong Li, Jun Wang, Yixuan Qiao, Hao Chen, Yihuan Yu, Xiaojun Yao, Peng Gao, Guotong Xie, Sen Song
2020 arXiv   pre-print
Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data.  ...  The pre-trained MolGNet can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of drug discovery tasks, including molecular properties prediction, drug-drug  ...  MPG Predict positive Nitroglycerin Pentaerythritol tetranitrate Isosorbide dinitrate Nicorandil Sildenafil Nitrate-Based drugs with attention weights Figure 6 : MPG provides explainability for DDI prediction  ... 
arXiv:2012.11175v1 fatcat:tnxekktvbfc6ro4alanzglc3fa
« Previous Showing results 1 — 15 out of 2,463 results