Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features

Sukwon Yun, Xin Liu, Yunhak Oh, Junseok Lee, Tianlong Chen, Tsuyoshi Murata, Chanyoung Park

Keywords: Graph-based Machine Learning, Missing Feature

Abstract: In real-world graphs, we often encounter missing feature situations where a few or the majority of node features, e.g., sensitive information, are missed. Although the recently proposed Feature Propagation algorithm mitigates such situations to some degree, it falls short when only partial features are available, sometimes performing worse than traditional structure-based graph models. To overcome this limitation, we spotlight a classical algorithm, Label Propagation (Oldie), and further illuminate its potential, especially when only a partial feature is available. Now called by Goodie, it takes a hybrid approach to obtain embeddings from the Label Propagation branch and Feature Propagation branch. To do so, we first design a GNN-based decoder that enables the Label Propagation branch to output hidden embeddings that align with those of the FP branch. Then, Goodie automatically captures the significance of structure and feature information thanks to the newly designed Structure-Feature Attention. Followed by a novel Pseudo-Label contrastive learning that differentiates the contribution of each positive pair within pseudo-labels originating from the LP branch, Goodie outputs the final prediction for the unlabeled nodes. Through extensive experiments, we demonstrate that our proposed model, Goodie, outperforms the existing state-of-the art methods not only when only a few features are available but also in abundantly available situations.

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11233