Filters








1,334 Hits in 6.2 sec

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks [article]

Chaoyang He, Keshav Balasubramanian, Emir Ceyani, Carl Yang, Han Xie, Lichao Sun, Lifang He, Liangwei Yang, Philip S. Yu, Yu Rong, Peilin Zhao, Junzhou Huang (+2 others)
2021 arXiv   pre-print
FedGraphNN is built on a unified formulation of graph FL and contains a wide range of datasets from different domains, popular GNN models, and FL algorithms, with secure and efficient system support.  ...  Graph Neural Network (GNN) research is rapidly growing thanks to the capacity of GNNs in learning distributed representations from graph-structured data.  ...  Supported GNN models and FL algorithms.  ... 
arXiv:2104.07145v2 fatcat:l7p3eb6tjbgztocugyohem2qea

Computing Graph Neural Networks: A Survey from Algorithms to Accelerators [article]

Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, Eduard Alarcón
2021 arXiv   pre-print
Besides of their novelty, GNNs are hard to compute due to their dependence on the input graph, their combination of dense and very sparse operations, or the need to scale to huge graphs in some applications  ...  Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers and the editorial team for their constructive criticism, which has helped improve the quality of the paper.  ... 
arXiv:2010.00130v3 fatcat:u5bcmjodcfdh7pew4nssjemdba

AliGraph: A Comprehensive Graph Neural Network Platform [article]

Rong Zhu, Kun Zhao, Hongxia Yang, Wei Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou
2019 arXiv   pre-print
However, it is challenging to provide an efficient graph storage and computation capabilities to facilitate GNN training and enable development of new GNN algorithms.  ...  By conducting extensive experiments on a real-world dataset with 492.90 million vertices, 6.82 billion edges and rich attributes, AliGraph performs an order of magnitude faster in terms of graph building  ...  GATNE Algorithm. This algorithm is designed to cope with graphs with heterogeneous and attribute information on both vertices and edges.  ... 
arXiv:1902.08730v1 fatcat:uvhnpnl3xzh2jft43vfowsuyze

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions [article]

Chen Gao, Yu Zheng, Nian Li, Yinfeng Li, Yingrong Qin, Jinghua Piao, Yuhan Quan, Jianxin Chang, Depeng Jin, Xiangnan He, Yong Li
2022 arXiv   pre-print
In this survey, we conduct a comprehensive review of the literature on graph neural network-based recommender systems.  ...  Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach to recommender systems.  ...  ACKNOWLEDGMENTS This work is supported by the National Key Research and Development Program of China under grant 2020AAA0106000.  ... 
arXiv:2109.12843v2 fatcat:qc5jocddvffwdp7ic5p3bv4aga

Computing Graph Neural Networks: A Survey from Algorithms to Accelerators

Sergi Abadal, Akshay Jain, Robert Guirado, Jorge López-Alonso, Eduard Alarcón
2022 ACM Computing Surveys  
Besides of their novelty, GNNs are hard to compute due to their dependence on the input graph, their combination of dense and very sparse operations, or the need to scale to huge graphs in some applications  ...  Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data.  ...  Abellán, and Manuel E. Acacio for the countless discussions on the topic.  ... 
doi:10.1145/3477141 fatcat:6ef4jh3hrvefnoytckqyyous3m

Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications [article]

Sai Munikoti, Deepesh Agarwal, Laya Das, Mahantesh Halappanavar, Balasubramaniam Natarajan
2022 arXiv   pre-print
These works can be classified into two categories: (1) algorithmic enhancement, where DRL and GNN complement each other for better utility; (2) application-specific enhancement, where DRL and GNN support  ...  Based on the review, we further analyze the applicability and benefits of fusing these two domains, especially in terms of increasing generalizability and reducing computational complexity.  ...  Traditional RL-based methods do not consider generation of new subgraphs within existing knowledge graphs, e.g., new or missing target entities.  ... 
arXiv:2206.07922v1 fatcat:cajusof5cjegvbvvctsrguz7nu

NeuGraph: Parallel Deep Neural Network Computation on Large Graphs

Lingxiao Ma, Zhi Yang, Youshan Miao, Jilong Xue, Ming Wu, Lidong Zhou, Yafei Dai
2019 USENIX Annual Technical Conference  
We present NeuGraph, a new framework that bridges the graph and dataflow models to support efficient and scalable parallel neural network computation on graphs.  ...  , and knowledge graphs.  ...  Acknowledgments We thank the anonymous reviewers for their valuable comments and suggestions.  ... 
dblp:conf/usenix/MaYMXWZD19 fatcat:zr2sgdhlefa3rj77j3hi3bsvnq

Survey on Graph Neural Network Acceleration: An Algorithmic Perspective [article]

Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye, Dongrui Fan, Shirui Pan, Yuan Xie
2022 arXiv   pre-print
Graph neural networks (GNNs) have been a hot spot of recent research and are widely utilized in diverse applications.  ...  However, with the use of huger data and deeper models, an urgent demand is unsurprisingly made to accelerate GNNs for more efficient execution.  ...  modifies input graphs based on the predicted probabilities; GAUG-O integrates the edge predictor and GNN model to jointly promote edge prediction and model accuracy.  ... 
arXiv:2202.04822v2 fatcat:ydnbs75uancljonaqjmaz6c4qa

AliGraph

Rong Zhu, Kun Zhao, Hongxia Yang, Wei Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou
2019 Proceedings of the VLDB Endowment  
However, it is challenging to provide an efficient graph storage and computation capabilities to facilitate GNN training and enable development of new GNN algorithms.  ...  By conducting extensive experiments on a real-world dataset with 492.90 million vertices, 6.82 billion edges and rich attributes, Ali-Graph performs an order of magnitude faster in terms of graph building  ...  GATNE Algorithm. This algorithm is designed to cope with graphs with heterogeneous and attribute information on both vertices and edges.  ... 
doi:10.14778/3352063.3352127 fatcat:w4eniwwlkvfuhhmobwrst37aqa

Reinforcement learning on graphs: A survey [article]

Nie Mingshuo, Chen Dongming, Wang Dongqi
2022 arXiv   pre-print
Graph mining tasks arise from many different application domains, ranging from social networks, transportation to E-commerce, etc., which have been receiving great attention from the theoretical and algorithmic  ...  In this survey, we provide a comprehensive overview of RL and graph mining methods and generalize these methods to Graph Reinforcement Learning (GRL) as a unified formulation.  ...  Relational GNNs based on artificial meta-paths [136] or meta-graphs [137] rely on inherent entity relationships and require the support of substantial domain knowledge. Zhong et al.  ... 
arXiv:2204.06127v2 fatcat:7wf6qxnxzza7xbiwjgjmrsrdjq

Few-Shot Learning on Graphs [article]

Chuxu Zhang, Kaize Ding, Jundong Li, Xiangliang Zhang, Yanfang Ye, Nitesh V. Chawla, Huan Liu
2022 arXiv   pre-print
Specifically, we first introduce FSLG challenges and bases, then categorize and summarize existing work of FSLG in terms of three major graph mining tasks at different granularity levels, i.e., node, edge  ...  , and graph.  ...  quickly adapt to a new few-shot task with gradient computation.  ... 
arXiv:2203.09308v2 fatcat:4pk3oacwsjgyzbywnmyurzrphq

Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges [article]

Savannah Thais, Paolo Calafiura, Grigorios Chachamis, Gage DeZoort, Javier Duarte, Sanmay Ganguly, Michael Kagan, Daniel Murnane, Mark S. Neubauer, Kazuhiro Terao
2022 arXiv   pre-print
With the wide-spread adoption of GNNs in industry, the HEP community is well-placed to benefit from rapid improvements in GNN latency and memory usage.  ...  Where previously these sets of data have been formulated as series or image data to match the available machine learning architectures, with the advent of graph neural networks (GNNs), these systems can  ...  A GNN-based PF algorithm was developed to operate on graphs with heterogeneous nodes corresponding to tracks and calorimeter clusters [46, 47] .  ... 
arXiv:2203.12852v2 fatcat:ohq4r53korhpbgy3yvl3q7tyay

Knowledge graph using resource description framework and connectionist theory

Ravi Lourdusamy, Xavierlal J Mattam
2020 Journal of Physics, Conference Series  
The weighted RDF in Graph Neural Network will represent the knowledge graph using RDF and connectionist theory.  ...  Interest in Knowledge Graph has peeked these years.  ...  Computer Vision, Natural Language Processing, forecasting traffic speed, volume or the density of roads in traffic networks, Graph-based Recommender systems and many other reasoning and prediction systems  ... 
doi:10.1088/1742-6596/1427/1/012001 fatcat:uqnd3tliczdhtarlu256inzjtu

DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs [article]

Da Zheng, Chao Ma, Minjie Wang, Jinjing Zhou, Qidong Su, Xiang Song, Quan Gan, Zheng Zhang, George Karypis
2021 arXiv   pre-print
To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints.  ...  DistDGL is based on the Deep Graph Library (DGL), a popular GNN development framework.  ...  INTRODUCTION Graph Neural Networks (GNNs) have shown success in learning from graph-structured data and have been applied to many graph applications in social networks, recommendation, knowledge graphs  ... 
arXiv:2010.05337v3 fatcat:6xvbvgvyczgsdhyfwolyhpmvwi

Heterogeneous Graph Neural Network Music Recommendation

Dean Cochran, Lorenzo Porcaro, Emilia Gómez
2022 Zenodo  
However, as the music recommendation system research community has witnessed the promising capabilities of graph neural networks, and as the limitations of a not having a publicly available, large scale  ...  With a primary focus on providing an machine learning recommendation system implementation, an analysis on the models' capabilities to provide recommendations to users whilst understanding user listening  ...  Graph Based Deep Learning Link Prediction As the development of deep learning in recommendation has seen a massive increase in novel graph-based algorithms, there has not been ample support by the MIR  ... 
doi:10.5281/zenodo.7116042 fatcat:vkal7h2ptbbdlpwtyfmta4nysi
« Previous Showing results 1 — 15 out of 1,334 results