Filters








6 Hits in 3.3 sec

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

Rami Al-Rfou, Bryan Perozzi, Dustin Zelle
2019 The World Wide Web Conference on - WWW '19  
We propose Deep Divergence Graph Kernels, an unsupervised method for learning representations over graphs that encodes a relaxed notion of graph isomorphism. Our method consists of three parts.  ...  Our experimental results show that Deep Divergence Graph Kernels can learn an unsupervised alignment between graphs, and that the learned representations achieve competitive results when used as features  ...  Next we introduce DDGK, our method for learning graph representations for Deep Divergence Graph Kernels in Section 4.3. Then in Section 4.4 we discuss how we train these representations.  ... 
doi:10.1145/3308558.3313668 dblp:conf/www/Al-RfouPZ19 fatcat:mhhomms6uffrvlvbfb5u62eire

Unsupervised Event Graph Representation and Similarity Learning on Biomedical Literature

Giacomo Frisoni, Gianluca Moro, Giulio Carlassare, Antonella Carbonaro
2021 Sensors  
Taking advantage of recent deep graph kernel solutions and pre-trained language models, we propose Deep Divergence Event Graph Kernels (DDEGK), an unsupervised inductive method to map events into low-dimensional  ...  However, very few works revolve around learning embeddings or similarity metrics for event graphs.  ...  Acknowledgments: We thank Eleonora Bertoni for her precious help in preparing the datasets, implementing the baseline, and conducting the experiments.  ... 
doi:10.3390/s22010003 pmid:35009544 pmcid:PMC8747118 fatcat:zghkmzt3wnf27cvh2p5tcvrvei

Deep Graph Similarity Learning: A Survey [article]

Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Philip S. Yu
2020 arXiv   pre-print
Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in  ...  Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications.  ...  Deep Divergence Graph Kernels In [11] , a model called Deep Divergence Graph Kernels (DDGK) is introduced to learn kernel functions for graph pairs.  ... 
arXiv:1912.11615v2 fatcat:mz6zq2wuhvhulcz67sgilmczoy

Deep graph similarity learning: a survey

Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Philip S. Yu
2021 Data mining and knowledge discovery  
Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in  ...  Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications.  ...  (2019) , a model called Deep Divergence Graph Kernels (DDGK) is introduced to learn kernel functions for graph pairs.  ... 
doi:10.1007/s10618-020-00733-5 fatcat:ip5p6rrgxva4fpn7nwifp3hkza

Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning [article]

Thilini Cooray, Ngai-Man Cheung
2022 arXiv   pre-print
Hence, this work proposes a new principle for unsupervised graph representation learning: Graph-wise Common latent Factor EXtraction (GCFX).  ...  To address this, we focus only on utilizing the current input graph for embedding learning.  ...  The authors are grateful for the discussion with Lu Wei.  ... 
arXiv:2112.08830v3 fatcat:dvtykp2hyjce5lumjapirdg6am

A Survey on Graph Representation Learning Methods [article]

Shima Khoshraftar, Aijun An
2022 arXiv   pre-print
GNN-based methods, on the other hand, are the application of deep learning on graph data.  ...  Many techniques are proposed for generating effective graph representation vectors.  ...  Non-GNN based deep learning. This type of dynamic graph embedding methods use deep learning models such as RNNs and autoencoders.  ... 
arXiv:2204.01855v2 fatcat:e5p76ipn6jgkzkajvucrvsa55e