@article{
 title = {Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules},
 type = {article},
 year = {2018},
 pages = {1-11},
 websites = {http://arxiv.org/abs/1811.09595},
 id = {5fd66d0c-7397-34ae-9cff-9f469a6ed809},
 created = {2021-08-04T13:05:08.165Z},
 file_attached = {true},
 profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2021-08-04T13:05:35.698Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size. Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes. To this end, we propose a novel multigraph network that learns from multi-relational graphs. We model learned edges with abstract meaning and experiment with different ways to fuse the representations extracted from annotated and learned edges, achieving competitive results on a variety of chemical classification benchmarks.},
 bibtype = {article},
 author = {Knyazev, Boris and Lin, Xiao and Amer, Mohamed R. and Taylor, Graham W.}
}

{"_id":"iHmnZgZf23Y2orw4w","bibbaseid":"knyazev-lin-amer-taylor-spectralmultigraphnetworksfordiscoveringandfusingrelationshipsinmolecules-2018","authorIDs":[],"author_short":["Knyazev, B.","Lin, X.","Amer, M., R.","Taylor, G., W."],"bibdata":{"title":"Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules","type":"article","year":"2018","pages":"1-11","websites":"http://arxiv.org/abs/1811.09595","id":"5fd66d0c-7397-34ae-9cff-9f469a6ed809","created":"2021-08-04T13:05:08.165Z","file_attached":"true","profile_id":"ad172e55-c0e8-3aa4-8465-09fac4d5f5c8","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2021-08-04T13:05:35.698Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"private_publication":false,"abstract":"Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size. Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes. To this end, we propose a novel multigraph network that learns from multi-relational graphs. We model learned edges with abstract meaning and experiment with different ways to fuse the representations extracted from annotated and learned edges, achieving competitive results on a variety of chemical classification benchmarks.","bibtype":"article","author":"Knyazev, Boris and Lin, Xiao and Amer, Mohamed R. and Taylor, Graham W.","bibtex":"@article{\n title = {Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules},\n type = {article},\n year = {2018},\n pages = {1-11},\n websites = {http://arxiv.org/abs/1811.09595},\n id = {5fd66d0c-7397-34ae-9cff-9f469a6ed809},\n created = {2021-08-04T13:05:08.165Z},\n file_attached = {true},\n profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2021-08-04T13:05:35.698Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size. Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes. To this end, we propose a novel multigraph network that learns from multi-relational graphs. We model learned edges with abstract meaning and experiment with different ways to fuse the representations extracted from annotated and learned edges, achieving competitive results on a variety of chemical classification benchmarks.},\n bibtype = {article},\n author = {Knyazev, Boris and Lin, Xiao and Amer, Mohamed R. and Taylor, Graham W.}\n}","author_short":["Knyazev, B.","Lin, X.","Amer, M., R.","Taylor, G., W."],"urls":{"Website":"http://arxiv.org/abs/1811.09595"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"knyazev-lin-amer-taylor-spectralmultigraphnetworksfordiscoveringandfusingrelationshipsinmolecules-2018","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","creationDate":"2020-02-11T20:02:58.159Z","downloads":0,"keywords":[],"search_terms":["spectral","multigraph","networks","discovering","fusing","relationships","molecules","knyazev","lin","amer","taylor"],"title":"Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules","year":2018,"dataSources":["9ZC4Jom7ygp8s9git","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}