Diversified Multiscale Graph Learning with Graph Self-Correction

Yuzhao Chen, Yatao Bian, Jiying Zhang, Xi Xiao, Tingyang Xv, Yu Rong
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:48-54, 2022.

Abstract

Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, we find that the classic ensemble strategy shows inferior performance while encountering the high homogeneity of the learnt representation, which is caused by the nature of existing graph pooling methods. To cope with this issue, we propose a diversified multiscale graph learning model equipped with two core ingredients: a graph self-correction mechanism to generate informative embedded graphs, and a diversity boosting regularizer to achieve a comprehensive characterization of the input graph. The proposed mechanism compensates the pooled graph with the lost information during the graph pooling process by feeding back the estimated residual graph, which serves as a plug-in component for popular graph pooling methods. Meanwhile, pooling methods enhanced with the self-correcting procedure encourage the discrepancy of node embeddings, and thus it contributes to the success of ensemble learning strategy. The proposed regularizer instead enhances the ensemble diversity at the graph-level embeddings by leveraging the interaction among individual classifiers. Extensive experiments on popular graph classification benchmarks show that the approaches lead to significant improvements over state-of-the-art graph pooling methods, and the ensemble multiscale graph learning models achieve superior enhancement.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-chen22a, title = {Diversified Multiscale Graph Learning with Graph Self-Correction}, author = {Chen, Yuzhao and Bian, Yatao and Zhang, Jiying and Xiao, Xi and Xv, Tingyang and Rong, Yu}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {48--54}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/chen22a/chen22a.pdf}, url = {https://proceedings.mlr.press/v196/chen22a.html}, abstract = {Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, we find that the classic ensemble strategy shows inferior performance while encountering the high homogeneity of the learnt representation, which is caused by the nature of existing graph pooling methods. To cope with this issue, we propose a diversified multiscale graph learning model equipped with two core ingredients: a graph self-correction mechanism to generate informative embedded graphs, and a diversity boosting regularizer to achieve a comprehensive characterization of the input graph. The proposed mechanism compensates the pooled graph with the lost information during the graph pooling process by feeding back the estimated residual graph, which serves as a plug-in component for popular graph pooling methods. Meanwhile, pooling methods enhanced with the self-correcting procedure encourage the discrepancy of node embeddings, and thus it contributes to the success of ensemble learning strategy. The proposed regularizer instead enhances the ensemble diversity at the graph-level embeddings by leveraging the interaction among individual classifiers. Extensive experiments on popular graph classification benchmarks show that the approaches lead to significant improvements over state-of-the-art graph pooling methods, and the ensemble multiscale graph learning models achieve superior enhancement.} }
Endnote
%0 Conference Paper %T Diversified Multiscale Graph Learning with Graph Self-Correction %A Yuzhao Chen %A Yatao Bian %A Jiying Zhang %A Xi Xiao %A Tingyang Xv %A Yu Rong %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-chen22a %I PMLR %P 48--54 %U https://proceedings.mlr.press/v196/chen22a.html %V 196 %X Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, we find that the classic ensemble strategy shows inferior performance while encountering the high homogeneity of the learnt representation, which is caused by the nature of existing graph pooling methods. To cope with this issue, we propose a diversified multiscale graph learning model equipped with two core ingredients: a graph self-correction mechanism to generate informative embedded graphs, and a diversity boosting regularizer to achieve a comprehensive characterization of the input graph. The proposed mechanism compensates the pooled graph with the lost information during the graph pooling process by feeding back the estimated residual graph, which serves as a plug-in component for popular graph pooling methods. Meanwhile, pooling methods enhanced with the self-correcting procedure encourage the discrepancy of node embeddings, and thus it contributes to the success of ensemble learning strategy. The proposed regularizer instead enhances the ensemble diversity at the graph-level embeddings by leveraging the interaction among individual classifiers. Extensive experiments on popular graph classification benchmarks show that the approaches lead to significant improvements over state-of-the-art graph pooling methods, and the ensemble multiscale graph learning models achieve superior enhancement.
APA
Chen, Y., Bian, Y., Zhang, J., Xiao, X., Xv, T. & Rong, Y.. (2022). Diversified Multiscale Graph Learning with Graph Self-Correction. Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:48-54 Available from https://proceedings.mlr.press/v196/chen22a.html.

Related Material