Timezone: »
Collective Inference (CI) is a procedure designed to boost weak relational classifiers, specially for node classification tasks. Graph Neural Networks (GNNs) are strong classifiers that have been used with great success. Unfortunately, most existing practical GNNs are not most-expressive (universal). Thus, it is an open question whether one can improve strong relational node classifiers, such as GNNs, with CI. In this work, we investigate this question and propose {\em collective learning} for GNNs ---a general collective classification approach for node representation learning that increases their representation power. We show that previous attempts to incorporate CI into GNNs fail to boost their expressiveness because they do not adapt CI's Monte Carlo sampling to representation learning. We evaluate our proposed framework with a variety of state-of-the-art GNNs. Our experiments show a consistent, significant boost in node classification accuracy ---regardless of the choice of underlying GNN--- for inductive node classification in partially-labeled graphs, across five real-world network datasets.
Author Information
Mengyue Hang (Purdue University)
Jennifer Neville (Purdue University)
Bruno Ribeiro (Purdue University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: A Collective Learning Framework to Boost GNN Expressiveness for Node Classification »
Thu. Jul 22nd 04:00 -- 06:00 PM Room None
More from the Same Authors
-
2022 : Asymmetry Learning for Counterfactual-invariant Classification in OOD Tasks »
Chandra Mouli Sekar · Bruno Ribeiro -
2022 Poster: On the Equivalence Between Temporal and Static Equivariant Graph Representations »
Jianfei Gao · Bruno Ribeiro -
2022 Spotlight: On the Equivalence Between Temporal and Static Equivariant Graph Representations »
Jianfei Gao · Bruno Ribeiro -
2021 Poster: Size-Invariant Graph Representations for Graph Classification Extrapolations »
Beatrice Bevilacqua · Yangze Zhou · Bruno Ribeiro -
2021 Oral: Size-Invariant Graph Representations for Graph Classification Extrapolations »
Beatrice Bevilacqua · Yangze Zhou · Bruno Ribeiro -
2019 Poster: Relational Pooling for Graph Representations »
Ryan Murphy · Balasubramaniam Srinivasan · Vinayak A Rao · Bruno Ribeiro -
2019 Oral: Relational Pooling for Graph Representations »
Ryan Murphy · Balasubramaniam Srinivasan · Vinayak A Rao · Bruno Ribeiro