Metraipolis › archive › dc_ac2cd4bad53f

PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning — arXiv:2609.04832

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04832
License (as archived)
CC0-1.0
Archived
2026-10-16T22:58:16.491Z
SHA-256 of the archived text
bb3d22d4b1d149b3ae318ebd2dd441d7224b11affe5b03c7d3576d46b9bdae8c
Stable URL of this page
https://metraipolis.com/documento/dc_ac2cd4bad53f

How to cite

PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning — arXiv:2609.04832 — arXiv (en), https://arxiv.org/abs/2609.04832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac2cd4bad53f (Metraipolis archive dc_ac2cd4bad53f, sha256 bb3d22d4b1d149b3ae318ebd2dd441d7224b11affe5b03c7d3576d46b9bdae8c)
BibTeX
@misc{dcac2cd4bad53f,
  title = {PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning — arXiv:2609.04832},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04832},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac2cd4bad53f; sha256 bb3d22d4b1d149b3ae318ebd2dd441d7224b11affe5b03c7d3576d46b9bdae8c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override reliable predictions. One-shot communication sharpens this tension because an unsuitable server return cannot be corrected later. We introduce PACE, which treats collaborative knowledge as a compact correction to a complete Local predictor rather than as its replacement. Each client uploads a rank-r update carrier and a diagonal sketch of propagated message moments. The server uses them to construct a propagation-aware, receiver-anchored correction, while the receiver retains its full Local model. Convex negative-log-likelihood calibration (CNLL) then selects one coefficient between Local and External logits using validation nodes; model parameters remain fixed and no feedback is sent. At Rank-6, personalized returns occupy 9.6-17.6% of dense tensor bytes across the six evaluated datasets. The correction receives nonzero weight and improves both Accuracy and weighted-F1 over Local on five datasets; on ogbn-arxiv, CNLL assigns zero predictive weight to the correction and preserves Local predictions exactly. Applying the same CNLL rule to matched baselines on three citation datasets does not account for these gains. The central result is therefore that a small transported correction can augment a complete Local model when receiver evidence supports it while leaving the Local prediction unchanged otherwise.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.04832 — 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 2026-10-16T22:31:32.192Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).