Metraipolis › archive › dc_357cf4ffec60

Efficient and Scalable Multi-View Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning — arXiv:2611.00511

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00511
License (as archived): CC0-1.0
Archived: 2026-11-03T18:35:16.694Z
SHA-256 of the archived text: 22ea91958cecac537c884e19568cdab1b8ed5d6556b94d554b8f358191130483
Stable URL of this page: https://metraipolis.com/documento/dc_357cf4ffec60

How to cite

Efficient and Scalable Multi-View Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning — arXiv:2611.00511 — arXiv (en), https://arxiv.org/abs/2611.00511 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_357cf4ffec60 (Metraipolis archive dc_357cf4ffec60, sha256 22ea91958cecac537c884e19568cdab1b8ed5d6556b94d554b8f358191130483)

BibTeX

@misc{dc357cf4ffec60,
  title = {Efficient and Scalable Multi-View Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning — arXiv:2611.00511},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00511},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_357cf4ffec60; sha256 22ea91958cecac537c884e19568cdab1b8ed5d6556b94d554b8f358191130483},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00511. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent years have witnessed the flourishing of self-supervised learning on heterogeneous graphs, e.g., masked autoencoder-based methods. However, existing methods 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 Multi-View Masked Auto Encoder (MVMAE), a novel, efficient, and scalable framework for heterogeneous graph self-supervised learning. First, MVMAE introduces a novel multi-view 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 and 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 pre-computes 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 multi-view 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 semi-supervised baselines, confirming its superior effectiveness and scalability. Our source code is released at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00511 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.432Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).