English

GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction

Machine Learning 2023-08-21 v1 Artificial Intelligence

Abstract

Self-supervised learning with masked autoencoders has recently gained popularity for its ability to produce effective image or textual representations, which can be applied to various downstream tasks without retraining. However, we observe that the current masked autoencoder models lack good generalization ability on graph data. To tackle this issue, we propose a novel graph masked autoencoder framework called GiGaMAE. Different from existing masked autoencoders that learn node presentations by explicitly reconstructing the original graph components (e.g., features or edges), in this paper, we propose to collaboratively reconstruct informative and integrated latent embeddings. By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge. Furthermore, we introduce a mutual information based reconstruction loss that enables the effective reconstruction of multiple targets. This learning objective allows us to differentiate between the exclusive knowledge learned from a single target and common knowledge shared by multiple targets. We evaluate our method on three downstream tasks with seven datasets as benchmarks. Extensive experiments demonstrate the superiority of GiGaMAE against state-of-the-art baselines. We hope our results will shed light on the design of foundation models on graph-structured data. Our code is available at: https://github.com/sycny/GiGaMAE.

Keywords

Cite

@article{arxiv.2308.09663,
  title  = {GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction},
  author = {Yucheng Shi and Yushun Dong and Qiaoyu Tan and Jundong Li and Ninghao Liu},
  journal= {arXiv preprint arXiv:2308.09663},
  year   = {2023}
}

Comments

Accepted by CIKM 2023

R2 v1 2026-06-28T11:58:55.479Z