English

Masked Graph Autoencoder with Non-discrete Bandwidths

Machine Learning 2024-02-07 v1 Social and Information Networks

Abstract

Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete edge masking and binary link reconstruction strategies are insufficient to learn topologically informative representations, from the perspective of message propagation on graph neural networks. These limitations include blocking message flows, vulnerability to over-smoothness, and suboptimal neighborhood discriminability. Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution. These masks restrict the amount of output messages for each edge, referred to as "bandwidths". We propose a novel, informative, and effective topological masked graph autoencoder using bandwidth masking and a layer-wise bandwidth prediction objective. We demonstrate its powerful graph topological learning ability both theoretically and empirically. Our proposed framework outperforms representative baselines in both self-supervised link prediction (improving the discrete edge reconstructors by at most 20%) and node classification on numerous datasets, solely with a structure-learning pretext. Our implementation is available at https://github.com/Newiz430/Bandana.

Keywords

Cite

@article{arxiv.2402.03814,
  title  = {Masked Graph Autoencoder with Non-discrete Bandwidths},
  author = {Ziwen Zhao and Yuhua Li and Yixiong Zou and Jiliang Tang and Ruixuan Li},
  journal= {arXiv preprint arXiv:2402.03814},
  year   = {2024}
}

Comments

Full version (17 pages, 8 figures, 12 tables), accepted by TheWebConf 2024 (WWW 2024)

R2 v1 2026-06-28T14:39:50.941Z