Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184206623> ?p ?o ?g. }
- W3184206623 abstract "Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step. In this paper, we propose a novel generalization of Factorized Bilinear (FB) layer to model the feature interactions in GCNs. FB performs two matrix-vector multiplications, that is, the weight matrix is multiplied with the outer product of the vector of hidden features from both sides. However, the FB layer suffers from the quadratic number of coefficients, overfitting and the spurious correlations due to correlations between channels of hidden representations that violate the i.i.d. assumption. Thus, we propose a compact FB layer by defining a family of summarizing operators applied over the quadratic term. We analyze proposed pooling operators and motivate their use. Our experimental results on multiple datasets demonstrate that the GFB-GCN is competitive with other methods for text classification." @default.
- W3184206623 created "2021-08-02" @default.
- W3184206623 creator A5002212263 @default.
- W3184206623 creator A5028028879 @default.
- W3184206623 date "2021-07-24" @default.
- W3184206623 modified "2023-09-28" @default.
- W3184206623 title "Graph Convolutional Network with Generalized Factorized Bilinear Aggregation." @default.
- W3184206623 cites W1593045043 @default.
- W3184206623 cites W1689688298 @default.
- W3184206623 cites W1736726159 @default.
- W3184206623 cites W1826790618 @default.
- W3184206623 cites W1832693441 @default.
- W3184206623 cites W2087159174 @default.
- W3184206623 cites W2094286023 @default.
- W3184206623 cites W2104657103 @default.
- W3184206623 cites W2131744502 @default.
- W3184206623 cites W2142498761 @default.
- W3184206623 cites W2153579005 @default.
- W3184206623 cites W2324076434 @default.
- W3184206623 cites W2407776548 @default.
- W3184206623 cites W2519887557 @default.
- W3184206623 cites W2521492858 @default.
- W3184206623 cites W2523679382 @default.
- W3184206623 cites W2551829638 @default.
- W3184206623 cites W2604314403 @default.
- W3184206623 cites W2788667846 @default.
- W3184206623 cites W2798995481 @default.
- W3184206623 cites W2905224888 @default.
- W3184206623 cites W2962711740 @default.
- W3184206623 cites W2962946486 @default.
- W3184206623 cites W2963012544 @default.
- W3184206623 cites W2963355447 @default.
- W3184206623 cites W2963626623 @default.
- W3184206623 cites W2963912736 @default.
- W3184206623 cites W2964121744 @default.
- W3184206623 cites W2964124573 @default.
- W3184206623 cites W2964301648 @default.
- W3184206623 cites W2964321699 @default.
- W3184206623 cites W2964876045 @default.
- W3184206623 cites W3023462908 @default.
- W3184206623 cites W3035135368 @default.
- W3184206623 cites W3124006607 @default.
- W3184206623 cites W3158166861 @default.
- W3184206623 cites W2585165747 @default.
- W3184206623 hasPublicationYear "2021" @default.
- W3184206623 type Work @default.
- W3184206623 sameAs 3184206623 @default.
- W3184206623 citedByCount "0" @default.
- W3184206623 crossrefType "posted-content" @default.
- W3184206623 hasAuthorship W3184206623A5002212263 @default.
- W3184206623 hasAuthorship W3184206623A5028028879 @default.
- W3184206623 hasConcept C11413529 @default.
- W3184206623 hasConcept C119857082 @default.
- W3184206623 hasConcept C129844170 @default.
- W3184206623 hasConcept C132525143 @default.
- W3184206623 hasConcept C134306372 @default.
- W3184206623 hasConcept C153180895 @default.
- W3184206623 hasConcept C154945302 @default.
- W3184206623 hasConcept C177148314 @default.
- W3184206623 hasConcept C205203396 @default.
- W3184206623 hasConcept C22019652 @default.
- W3184206623 hasConcept C2524010 @default.
- W3184206623 hasConcept C31972630 @default.
- W3184206623 hasConcept C33923547 @default.
- W3184206623 hasConcept C41008148 @default.
- W3184206623 hasConcept C50644808 @default.
- W3184206623 hasConcept C70437156 @default.
- W3184206623 hasConcept C80444323 @default.
- W3184206623 hasConcept C97256817 @default.
- W3184206623 hasConceptScore W3184206623C11413529 @default.
- W3184206623 hasConceptScore W3184206623C119857082 @default.
- W3184206623 hasConceptScore W3184206623C129844170 @default.
- W3184206623 hasConceptScore W3184206623C132525143 @default.
- W3184206623 hasConceptScore W3184206623C134306372 @default.
- W3184206623 hasConceptScore W3184206623C153180895 @default.
- W3184206623 hasConceptScore W3184206623C154945302 @default.
- W3184206623 hasConceptScore W3184206623C177148314 @default.
- W3184206623 hasConceptScore W3184206623C205203396 @default.
- W3184206623 hasConceptScore W3184206623C22019652 @default.
- W3184206623 hasConceptScore W3184206623C2524010 @default.
- W3184206623 hasConceptScore W3184206623C31972630 @default.
- W3184206623 hasConceptScore W3184206623C33923547 @default.
- W3184206623 hasConceptScore W3184206623C41008148 @default.
- W3184206623 hasConceptScore W3184206623C50644808 @default.
- W3184206623 hasConceptScore W3184206623C70437156 @default.
- W3184206623 hasConceptScore W3184206623C80444323 @default.
- W3184206623 hasConceptScore W3184206623C97256817 @default.
- W3184206623 hasOpenAccess W3184206623 @default.
- W3184206623 hasRelatedWork W2062403535 @default.
- W3184206623 hasRelatedWork W2064788805 @default.
- W3184206623 hasRelatedWork W20696413 @default.
- W3184206623 hasRelatedWork W2081082212 @default.
- W3184206623 hasRelatedWork W2237846767 @default.
- W3184206623 hasRelatedWork W2406632313 @default.
- W3184206623 hasRelatedWork W2620611182 @default.
- W3184206623 hasRelatedWork W2783898497 @default.
- W3184206623 hasRelatedWork W2895339336 @default.
- W3184206623 hasRelatedWork W2897433210 @default.
- W3184206623 hasRelatedWork W2911276231 @default.
- W3184206623 hasRelatedWork W2997767360 @default.