Automated Loss function Search for Class-imbalanced Node Classification

Xinyu Guo, Kai Wu, Xiaoyu Zhang, Jing Liu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16958-16973, 2024.

Abstract

Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node representations remains a challenging endeavor. The engineering of loss functions has shown promising potential in addressing this issue. It involves the meticulous design of loss functions, utilizing information about the quantities of nodes in different categories and the network’s topology to learn unbiased node representations. However, the design of these loss functions heavily relies on human expert knowledge and exhibits limited adaptability to specific target tasks. In this paper, we introduce a high-performance, flexible, and generalizable automated loss function search framework to tackle this challenge. Across 15 combinations of graph neural networks and datasets, our framework achieves a significant improvement in performance compared to state-of-the-art methods. Additionally, we observe that homophily in graph-structured data significantly contributes to the transferability of the proposed framework.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-guo24h, title = {Automated Loss function Search for Class-imbalanced Node Classification}, author = {Guo, Xinyu and Wu, Kai and Zhang, Xiaoyu and Liu, Jing}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {16958--16973}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/guo24h/guo24h.pdf}, url = {https://proceedings.mlr.press/v235/guo24h.html}, abstract = {Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node representations remains a challenging endeavor. The engineering of loss functions has shown promising potential in addressing this issue. It involves the meticulous design of loss functions, utilizing information about the quantities of nodes in different categories and the network’s topology to learn unbiased node representations. However, the design of these loss functions heavily relies on human expert knowledge and exhibits limited adaptability to specific target tasks. In this paper, we introduce a high-performance, flexible, and generalizable automated loss function search framework to tackle this challenge. Across 15 combinations of graph neural networks and datasets, our framework achieves a significant improvement in performance compared to state-of-the-art methods. Additionally, we observe that homophily in graph-structured data significantly contributes to the transferability of the proposed framework.} }
Endnote
%0 Conference Paper %T Automated Loss function Search for Class-imbalanced Node Classification %A Xinyu Guo %A Kai Wu %A Xiaoyu Zhang %A Jing Liu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-guo24h %I PMLR %P 16958--16973 %U https://proceedings.mlr.press/v235/guo24h.html %V 235 %X Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node representations remains a challenging endeavor. The engineering of loss functions has shown promising potential in addressing this issue. It involves the meticulous design of loss functions, utilizing information about the quantities of nodes in different categories and the network’s topology to learn unbiased node representations. However, the design of these loss functions heavily relies on human expert knowledge and exhibits limited adaptability to specific target tasks. In this paper, we introduce a high-performance, flexible, and generalizable automated loss function search framework to tackle this challenge. Across 15 combinations of graph neural networks and datasets, our framework achieves a significant improvement in performance compared to state-of-the-art methods. Additionally, we observe that homophily in graph-structured data significantly contributes to the transferability of the proposed framework.
APA
Guo, X., Wu, K., Zhang, X. & Liu, J.. (2024). Automated Loss function Search for Class-imbalanced Node Classification. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:16958-16973 Available from https://proceedings.mlr.press/v235/guo24h.html.

Related Material