Przeskocz do nawigacji głównej Przeskocz do wyszukiwania Przeskocz do głównej treści

MobileGCN applied to low-dimensional node feature learning

  • Wei Dong
  • , Junsheng Wu
  • , Zongwen Bai
  • , Yaoqi Hu
  • , Weigang Li
  • , Wei Qiao
  • , Marcin Woźniak
  • Northwestern Polytechnical University Xian
  • Yan'an University
  • Xi'an Research Institute of China Coal Technology & Engineering Group Corp

Wyniki badań: Wkład do czasopisma › Artykuł › recenzja

37 Cytowania z bazy Scopus

Abstrakt

The idea of the paper concentrates on an iterative learning process in Graph Convolution Networks (GCNs) involved in two vital steps: one is a message propagation (message passing) step to aggregate neighboring node features via aggregators performed, and another is an encoding output step to encode node feature representations by using updaters. In our model, we propose a novel affinity-aware encoding as an updater in GCNs, which aggregates the neighboring nodes of a node while updating this node's features. By utilizing affinity values of our encoding, we order the neighboring nodes to determine the correspondence between encoding functions and the neighboring nodes. Furthermore, to explicitly reduce the model size, we propose a lightweight variant of our updater that integrates Depth-wise Separable Convolution (DSC) into it, namely Depth-wise Separable Graph Convolution (DSGC). Comprehensive experiments conducted on graph data demonstrate that our models’ accuracy improved significantly for graphs of low-dimensional node features. Also, performed in the low-dimensional node feature space we provide state-of-the-art results on two metrics (Macro-f1 and Matthews correlation coefficient (MCC)). Besides, our models are robust when taking different low-dimensional feature selection strategies.

Język oryginałuangielski
Numer artykułu107788
CzasopismoPattern Recognition
Tom112
Identyfikatory DOI
Status publikacjiOpublikowano - kwi 2021

Obszary tematyczne ASJC Scopus

  • Oprogramowanie
  • Przetwarzanie sygnałów
  • Rozpoznawanie obrazów i wzorów
  • Sztuczna inteligencja

Fingerprint

Zanurz się w tematy badawcze publikacji „MobileGCN applied to low-dimensional node feature learning”. Razem tworzą niepowtarzalny odcisk palca.

Cytowanie