Metraipolis › archive › dc_dcaff4efe08e

Multi-Source Wasserstein Distributionally Robust Graph Learning — arXiv:2608.19914

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.19914
License (as archived): CC0-1.0
Archived: 2026-10-18T11:48:20.734Z
SHA-256 of the archived text: f567f8e1ee6d73780a77786360529d56e52402be1ad085937b011a2eb8e32ef4
Stable URL of this page: https://metraipolis.com/documento/dc_dcaff4efe08e

How to cite

Multi-Source Wasserstein Distributionally Robust Graph Learning — arXiv:2608.19914 — arXiv (en), https://arxiv.org/abs/2608.19914 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcaff4efe08e (Metraipolis archive dc_dcaff4efe08e, sha256 f567f8e1ee6d73780a77786360529d56e52402be1ad085937b011a2eb8e32ef4)

BibTeX

@misc{dcdcaff4efe08e,
  title = {Multi-Source Wasserstein Distributionally Robust Graph Learning — arXiv:2608.19914},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19914},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcaff4efe08e; sha256 f567f8e1ee6d73780a77786360529d56e52402be1ad085937b011a2eb8e32ef4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19914. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing complex network topologies from data is a fundamental challenge in cybernetics and graph signal processing, with applications in neuroscience, sensor, and social networks. In practice, target-domain samples are scarce while heterogeneous source-domain data are abundant. Fusing these sources is challenging: Euclidean averaging works for homogeneous sources but degrades sharply as inter-source divergence grows, collapsing distinct geometries into an inflated, biased consensus. We exploit the Wasserstein metric's distribution-preserving properties to counter heterogeneity while preserving each source's intrinsic geometry. We propose MS-WDRO, a multi-source Wasserstein distributionally robust graph learning framework that fuses heterogeneous sources via their weighted Wasserstein barycenter, a geometrically principled nominal distribution, then builds an ambiguity ball around it to hedge residual uncertainty. Minimizing worst-case risk yields a tractable regularized Laplacian estimator solved efficiently via a provably convergent ADMM scheme. We establish non-asymptotic guarantees: a finite-sample concentration bound for the empirical barycenter, a pooling bias lower bound proving naive aggregation is suboptimal, and an out-of-sample excess risk bound decaying at a parametric rate with only logarithmic dependence on source count. To calibrate hyperparameters governing robustness, sparsity, and source fusion, we unroll the solver into a differentiable architecture trained end-to-end, achieving data-adaptive calibration beyond cross-validation while retaining interpretability. Experiments on synthetic benchmarks and the multi-site ABIDE~I neuroimaging dataset show MS-WDRO consistently outperforms seven baselines in graph recovery, sample efficiency, and downstream diagnostic utility, with the largest gains in the sample-scarce regime.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.19914 — 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 2026-10-18T11:47:43.327Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).