Metraipolis › archive › dc_2e4fec0b3a8d

MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks — arXiv:2609.00696

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00696
License (as archived)
CC0-1.0
Archived
2026-10-17T06:52:11.641Z
SHA-256 of the archived text
d5af566bbc746c78c025036f99f342b07f241478ae3a07b760ae4a036dbcab6d
Stable URL of this page
https://metraipolis.com/documento/dc_2e4fec0b3a8d

How to cite

MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks — arXiv:2609.00696 — arXiv (en), https://arxiv.org/abs/2609.00696 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e4fec0b3a8d (Metraipolis archive dc_2e4fec0b3a8d, sha256 d5af566bbc746c78c025036f99f342b07f241478ae3a07b760ae4a036dbcab6d)
BibTeX
@misc{dc2e4fec0b3a8d,
  title = {MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks — arXiv:2609.00696},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00696},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e4fec0b3a8d; sha256 d5af566bbc746c78c025036f99f342b07f241478ae3a07b760ae4a036dbcab6d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00696. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph data across diverse domains can expose valuable relational information to unauthorized representation learning, creating a pressing need for protection against such misuse. Unlearnable examples offer a data-level defense by perturbing a training release so that models trained on it fail to generalize to clean data. Existing methods generate unlearnable graph examples for only a specified downstream task. Consequently, a release protected against one task may remain learnable for other plausible uses, including node classification, graph classification, and link prediction, which the data owner cannot anticipate. We introduce MUGEN, to our knowledge the first framework for generating unlearnable graph examples that jointly protect all enabled tasks. From one clean dataset, MUGEN produces a single feature-perturbed release that protects every enabled task through a shared GNN encoder and task-specific heads. We devise a Task-Aligned Separability Objective (TASO), which leverages task prediction and classwise separability to strengthen unlearnability and its transfer across GNN backbones and enabled tasks. We further introduce Type-Adaptive Perturbation (TAP), which tailors perturbation optimization to node-attribute type, with direct search over feasible hard flips that accept only loss-improving updates for discrete node attributes and customized gradient-based updates for continuous node features, thereby enabling strong unlearnability across both settings. Experiments across five benchmarks, four backends and three learning paradigms demonstrate that MUGEN generates transferable unlearnable graph examples across GNN backbones and all three tasks, and remains effective under adversarial training and data augmentation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00696 — 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 2026-10-17T06:41:55.812Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).