Oct 2026· IEEE Transactions on Neural Networks and Learning Systems· Vol PP, pp. 1-15· 0 citations· 42 references
MedicineComputer Science
TL;DR
The multiview masked autoencoder (MVMAE) is proposed-a novel, efficient, and scalable framework for heterogeneous graph SSL that consistently outperforms state-of-the-art self-supervised and even semisupervised baselines, confirming its superior effectiveness and scalability.
Abstract
Recent years have witnessed the flourishing of self-supervised learning (SSL) on heterogeneous graphs, e.g., masked autoencoder (MAE)-based methods. However, existing MAE-based methods mostly suffer from three issues, including the prohibitive computational cost of constructing meta-path-induced subgraphs, the limitations of uniform random masking, and the suboptimal objective of reconstructing potentially noisy or uninformative original node features. To address these issues, we propose the multiview masked autoencoder (MVMAE)-a novel, efficient, and scalable framework for heterogeneous graph SSL. First, MVMAE introduces a novel multiview mask-then-reconstruct strategy. Instead of masking individual nodes or features, MVMAE randomly masks entire meta-path views and guides the model to reconstruct their representations from remaining visible views. This approach shifts the learning objective to a high-level, semantic task, providing a more robust and informative supervisory signal that is effective even when initial node features are absent or flawed. Then, to handle the computational demands, MVMAE employs an efficient offline aggregation mechanism that precomputes and reuses representations for each meta-path view, completely avoiding the costly construction of meta-path-induced subgraphs. Next, to fuse the representations of each view, MVMAE uses a Transformer-based multiview fusion encoder to capture the complex correlations between views, and a deliberately simple MLP decoder to compel the encoder to learn highly expressive and robust node representations. Extensive experiments on six real-world datasets, including three large-scale graphs, demonstrate that MVMAE consistently outperforms state-of-the-art self-supervised and even semisupervised baselines, confirming its superior effectiveness and scalability. Our source code is released at https://github.com/hcmdgh/MVMAE.
Graph-structured data is ubiquitous, yet labeled graph data remains scarce and expensive, limiting the effectiveness of supervised graph neural networks (GNNs). To address this, self-supervised learning (SSL) has emerged as a promising paradigm to pre-train GNNs on unlabeled graphs. However, existing SSL methods typica...
Rong-Kun Li· Applied and Computational En...· 0 citations
Graph-level out-of-distribution (OOD) generalization is critical for deploying graph neural networks in real-world applications where distribution shifts are inevitable. Existing approaches typically require class labels during representation learning to decide which substructures are predictive, limiting their applica...
Tian-Jun Yao, Cheng-Hu Xi, Xin-Yang Li et al.· 0 citations
Graph contrastive learning (GCL) has emerged as an effective paradigm for learning discriminative graph representations. However, applying GCL to large-scale graphs remains challenging, since conventional GCL frameworks often rely on message-passing GNN encoders and pairwise contrastive objectives, which may introduce...
Graph Contrastive Learning (GCL) has achieved remarkable success in self-supervised representation learning by maximizing agreement between augmented views of a graph. Although augmented view generation is the central step in GCL, existing models rely on stochastic augmentation of the input graph, such as edge perturba...
Muhammad Ifte Khairul Islam, Tanvir Hossain, Esra Akbas· 0 citations
Accurate clustering of single-cell RNA sequencing (scRNA-seq) data is essential for cell type annotation and cellular heterogeneity inference, but existing methods are still limited by local gene co-expression redundancy and pairwise graph modeling, which hinder the capture of cross-module biological semantics and high...
Yao-Wei Cao, Xin-Yu Du, Zhen-Hua Yu· IEEE transactions on computa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.