A Collective Learning Framework to Boost GNN Expressiveness for Node Classification

Mengyue Hang, Jennifer Neville, Bruno Ribeiro
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4040-4050, 2021.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-hang21a, title = {A Collective Learning Framework to Boost GNN Expressiveness for Node Classification}, author = {Hang, Mengyue and Neville, Jennifer and Ribeiro, Bruno}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {4040--4050}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/hang21a/hang21a.pdf}, url = {https://proceedings.mlr.press/v139/hang21a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T A Collective Learning Framework to Boost GNN Expressiveness for Node Classification %A Mengyue Hang %A Jennifer Neville %A Bruno Ribeiro %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-hang21a %I PMLR %P 4040--4050 %U https://proceedings.mlr.press/v139/hang21a.html %V 139 %X 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.
APA
Hang, M., Neville, J. & Ribeiro, B.. (2021). A Collective Learning Framework to Boost GNN Expressiveness for Node Classification. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:4040-4050 Available from https://proceedings.mlr.press/v139/hang21a.html.

Related Material