11,398 Hits in 5.9 sec

Neural Subgraph Matching [article]

Rex Ying, Zhaoyu Lou, Jiaxuan You, Chengtao Wen, Arquimedes Canedo, Jure Leskovec
2020 arXiv   pre-print
NeuroMatch decomposes query and target graphs into small subgraphs and embeds them using graph neural networks.  ...  Trained to capture geometric constraints corresponding to subgraph relations, NeuroMatch then efficiently performs subgraph matching directly in the embedding space.  ...  At the embedding stage, we decompose the target graph G T into many sub-networks G u : For every node u ∈ G T we extract a k-hop sub-network G u around u and use a GNN to obtain an embedding for u, capturing  ... 
arXiv:2007.03092v2 fatcat:iukf3larbbdt5mgyblw3lca5cq

Embedding Logical Queries on Knowledge Graphs [article]

William L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, Jure Leskovec
2019 arXiv   pre-print
Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities.  ...  For instance, given an incomplete biological knowledge graph, we might want to predict "em what drugs are likely to target proteins involved with both diseases X and Y?"  ...  Acknowledgements The authors thank Alex Ratner, Stephen Bach, and Michele Catasta for their helpful discussions and comments on early drafts.  ... 
arXiv:1806.01445v4 fatcat:s6qwg3sosrflnbqb372v45ha6e

Mining Dynamic Graph Streams for Predictive Queries Under Resource Constraints [chapter]

Xuanming Liu, Tingjian Ge
2020 Lecture Notes in Computer Science  
We present our approach with two major components: a Count-Fading sketch and an online incremental embedding algorithm. We answer predictive relationship queries using the embedding results.  ...  Answering predictive relationship queries over such a stream is very challenging as the heterogeneous graph streams imply complex topological and temporal correlations of knowledge facts, as well as fast  ...  Graph Stream Embedding and Query Answering To answer predictive relationship queries, we devise a general method based on graph embedding.  ... 
doi:10.1007/978-3-030-47436-2_3 fatcat:atsjmflmmrfofivhzacqcwc5hi

Grounded Graph Decoding Improves Compositional Generalization in Question Answering [article]

Yu Gai, Paras Jain, Wendi Zhang, Joseph E. Gonzalez, Dawn Song, Ion Stoica
2021 arXiv   pre-print
By predicting a structured graph containing conjunctions of query clauses, we learn a group invariant representation without making assumptions on the target domain.  ...  We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism.  ...  Acknowledgments We thank Lisa Dunlap, Daniel Furrer, Ajay Jain, Daniel Rothchild, Nathan Scales, Rishabh Singh, Justin Wong and Marc van Zee for their help.  ... 
arXiv:2111.03642v1 fatcat:ily6hsjqbzenlljuxc35jaauni

GraphStep: A System Architecture for Sparse-Graph Algorithms

Michael deLorimier, Nachiket Kapre, Nikil Mehta, Dominic Rizzo, Ian Eslick, Raphael Rubin, Tomas Uribe, Thomas Jr. Knight, Andre DeHon
2006 2006 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines  
To avoid this "memory wall," we introduce a concurrent system architecture for sparse graph algorithms that places graph nodes in small distributed memories paired with specialized graph processing nodes  ...  This gives us a scalable way to map these applications so that they can exploit the high-bandwidth and low-latency capabilities of embedded memories (e.g., FPGA Block RAMs).  ...  Consequently, we introduce a new concurrent system architecture for sparse graph-processing algorithms.  ... 
doi:10.1109/fccm.2006.45 dblp:conf/fccm/DeLorimierKMRERUKD06 fatcat:nhs4imph3rdnljnn5sslljioeu

SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs [article]

Hongyu Ren, Hanjun Dai, Bo Dai, Xinyun Chen, Denny Zhou, Jure Leskovec, Dale Schuurmans
2021 arXiv   pre-print
Embedding-based methods solve both tasks by first computing an embedding for each entity and relation, then using them to form predictions.  ...  which KG entities satisfy a given logical query.  ...  on Marius, Matthias Fey for discussions on sparse embeddings.  ... 
arXiv:2110.14890v2 fatcat:4jxu2pz6cbdshbhetuqnbpwzju


Hongyu Ren, Hanjun Dai, Bo Dai, Xinyun Chen, Denny Zhou, Jure Leskovec, Dale Schuurmans
2022 Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining  
Embeddingbased methods solve both tasks by first computing an embedding for each entity and relation, then using them to form predictions.  ...  Using a single machine SMORE can perform multi-hop reasoning in Freebase KG (86M entities, 338M edges), which is 1,500× larger than previously considered KGs.  ...  on Marius, Matthias Fey for discussions on sparse embeddings.  ... 
doi:10.1145/3534678.3539405 fatcat:4ulwnicturfb5f3gdalpp2oq2y

r-GAT: Relational Graph Attention Network for Multi-Relational Graphs [article]

Meiqi Chen, Yuan Zhang, Xiaoyu Kou, Yuntao Li, Yan Zhang
2021 arXiv   pre-print
We further propose a query-aware attention mechanism for subsequent tasks to select useful aspects.  ...  This enables us to aggregate neighborhood information for the current aspect using relation features.  ...  Link Prediction Dataset We use two benchmark knowledge graph datasets to evaluate the performance of r-GAT on link prediction task: FB15k-237 (Toutanova et al. 2015) is a subset of FB15k (Bordes et  ... 
arXiv:2109.05922v1 fatcat:v5jrhtnxl5ec5mjujiogvoktke

Cyber-All-Intel: An AI for Security related Threat Intelligence [article]

Sudip Mittal, Anupam Joshi, Tim Finin
2019 arXiv   pre-print
We have also created a query engine and an alert system that can be used by an analyst to find actionable cybersecurity insights.  ...  It uses multiple knowledge representations like, vector spaces and knowledge graphs in a 'VKG structure' to store incoming intelligence.  ...  In the query mentioned above, search queries, for the topk nearest neighborhood search should be performed using the embeddings, and the list, inf er queries on the knowledge graph part.  ... 
arXiv:1905.02895v1 fatcat:7gzaaklhgbaydi7nmbz2qxfh3e

Efficient and Faster Method for Query-Dependent Local Landmark Scheme

Sumedh S . Khodwe
2015 International Journal of Innovative Research in Computer and Communication Engineering  
All of these existing systems make use of landmark embedding approach, that select a set of graph nodes as landmarks and then find the earliest distances from each landmark to all nodes.  ...  In early days the size of graph become huge that's why finding shortest distance between queried node is necessary.  ...  Verity of methods are available to find shortest distance between two queried node in large graph, in the landmark embedding the nodes of the graph are selected as landmark, such method is used online  ... 
doi:10.15680/ijircce.2015.0307013 fatcat:5hr6lgtqknevria6ruadjky7xq

Execution Time Prediction for Cypher Queries in the Neo4j Database Using a Learning Approach

Zhenzhen He, Jiong Yu, Binglei Guo
2022 Symmetry  
Inspired by machine-learning methods and graph query optimization technologies, we used the RBF neural network as a prediction model to train and predict the execution time of Cypher queries.  ...  Meanwhile, the corresponding query pattern features, graph data features, and query plan features were fused together and then used to train our prediction models.  ...  In [31] , the embedding approach was proposed for concurrent queries to predict performance, and the authors used the graph-structured model to capture the operator feature and the correlations between  ... 
doi:10.3390/sym14010055 fatcat:cdfpjoe25fadzf52jnvmnyr73y

Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs [article]

Sudip Mittal, Anupam Joshi, Tim Finin
2017 arXiv   pre-print
We also demonstrate and evaluate the VKG structure and the query processing engine by developing a system called Cyber-All-Intel for knowledge extraction, representation and querying in an end-to-end pipeline  ...  We have created a query processing engine that takes complex queries and decomposes them into subqueries optimized to run on the respective knowledge graph or vector view of a VKG.  ...  In both example queries mentioned above, search queries, for the top-k nearest neighborhood search should be performed using the embeddings, and the list, inf er queries on the knowledge graph part.  ... 
arXiv:1708.03310v2 fatcat:7mxviyv5fbes7dz6wruwg72ulu

Graph-RISE: Graph-Regularized Image Semantic Embedding [article]

Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, Sujith Ravi
2019 arXiv   pre-print
In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M  ...  Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking.  ...  Thomas Leung for the reviews and suggestions. We also thank Expander, Image Understanding and several related teams for the technical support.  ... 
arXiv:1902.10814v1 fatcat:m5a6vg7yz5g5bcayu3st7lua2m

ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest [article]

Yuezihan Jiang, Yu Cheng, Hanyu Zhao, Wentao Zhang, Xupeng Miao, Yu He, Liang Wang, Zhi Yang, Bin Cui
2022 arXiv   pre-print
Deployed as a large-scale distributed system, ZOOMER supports graphs with billions of nodes for training and thousands of requests per second for serving.  ...  We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs.  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their valuable suggestions. This work is supported by NSFC (No. 61832001, 61972004), Beijing Academy of Artificial Intelligence (BAAI) and Alibaba.  ... 
arXiv:2203.12596v1 fatcat:azfdiue4evh3lmocvvrjq45g2i

Performance Evaluation of the Karma Provenance Framework for Scientific Workflows [chapter]

Yogesh L. Simmhan, Beth Plale, Dennis Gannon, Suresh Marru
2006 Lecture Notes in Computer Science  
The Karma provenance framework provides a means to collect workflow, process, and data provenance from data-driven scientific workflows and is used in the Linked Environments for Atmospheric Discovery  ...  Our study finds that Karma scales exceedingly well for collecting and querying provenance records, showing linear or sub-linear scaling with increasing number of provenance records and clients when tested  ...  The authors would like to thank Paul Groth from the University of Southampton for helping us deploy the PReServ server, the members of the LEAD team for their support and feedback on our work, and Abhijit  ... 
doi:10.1007/11890850_23 fatcat:gawmanmqkze6zpig25fo3pddi4
« Previous Showing results 1 — 15 out of 11,398 results