---
res:
  bibo_abstract:
  - Current GNN architectures use a vertex neighborhood aggregation scheme, which
    limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman
    (WL) graph isomorphism test. Here, we propose a novel graph convolution operator
    that is based on the 2-dimensional WL test. We formally show that the resulting
    2-WL-GNN architecture is more discriminative than existing GNN approaches. This
    theoretical result is complemented by experimental studies using synthetic and
    real data. On multiple common graph classification benchmarks, we demonstrate
    that the proposed model is competitive with state-of-the-art graph kernels and
    GNNs.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Clemens
      foaf_name: Damke, Clemens
      foaf_surname: Damke
      foaf_workInfoHomepage: http://www.librecat.org/personId=48192
    orcid: 0000-0002-0455-0048
  - foaf_Person:
      foaf_givenName: Vitaly
      foaf_name: Melnikov, Vitaly
      foaf_surname: Melnikov
      foaf_workInfoHomepage: http://www.librecat.org/personId=58747
  - foaf_Person:
      foaf_givenName: Eyke
      foaf_name: Hüllermeier, Eyke
      foaf_surname: Hüllermeier
      foaf_workInfoHomepage: http://www.librecat.org/personId=48129
  bibo_volume: 129
  dct_date: 2020^xs_gYear
  dct_language: eng
  dct_publisher: PMLR@
  dct_subject:
  - graph neural networks
  - Weisfeiler-Lehman test
  - cycle detection
  dct_title: A Novel Higher-order Weisfeiler-Lehman Graph Convolution@
...