Metraipolis › archive › dc_f6a21985e73d
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction — arXiv:2608.29369
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29369
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:25:52.754Z
- SHA-256 of the archived text
917c11b1a938774c685ae440ee8998ff58c04f5e5154ecc972fcda386b6fdcad- Stable URL of this page
https://metraipolis.com/documento/dc_f6a21985e73d
How to cite
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction — arXiv:2608.29369 — arXiv (en), https://arxiv.org/abs/2608.29369 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6a21985e73d (Metraipolis archive dc_f6a21985e73d, sha256 917c11b1a938774c685ae440ee8998ff58c04f5e5154ecc972fcda386b6fdcad)
BibTeX
@misc{dcf6a21985e73d,
title = {Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction — arXiv:2608.29369},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29369},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6a21985e73d; sha256 917c11b1a938774c685ae440ee8998ff58c04f5e5154ecc972fcda386b6fdcad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29369. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatio-temporal graphs are widely used in modeling complex dynamic processes such as temporal forecasting, molecular dynamics, and healthcare monitoring. Recently, stringent privacy regulations such as GDPR and CCPA have introduced significant new challenges for existing spatio-temporal graph models, requiring complete unlearning of unauthorized data. Since each node in a spatio-temporal graph diffuses information globally across both spatial and temporal dimensions, existing unlearning methods primarily designed for static graphs and localized data removal cannot efficiently erase a single node without incurring costs nearly equivalent to full model retraining. To address this, we propose CallosumNet, a spatio-temporal graph unlearning framework biologically inspired by the corpus callosum structure. CallosumNet makes two key technical contributions: (1) it reconstructs subgraphs using biologically-inspired virtual edges; and (2) it restores interlinked spatio-temporal dependencies among subgraphs via a lightweight meta-graph integration layer. Empirical results on four diverse real-world datasets show that CallosumNet achieves complete unlearning while maintaining accuracy very close to the gold model. The code is publicly available at this https URL . Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CR). Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.29369 — 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 2026-10-17T08:10:59.902Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).