Metraipolis › archive › dc_5f061ebaaa66
Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification — arXiv:2610.34140
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34140
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:00:40.541Z
- SHA-256 of the archived text
42d20ec1d148a95dea9bcf39105353b2c01af8169678019061be240364b8aa2b- Stable URL of this page
https://metraipolis.com/documento/dc_5f061ebaaa66
How to cite
Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification — arXiv:2610.34140 — arXiv (en), https://arxiv.org/abs/2610.34140 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f061ebaaa66 (Metraipolis archive dc_5f061ebaaa66, sha256 42d20ec1d148a95dea9bcf39105353b2c01af8169678019061be240364b8aa2b)
BibTeX
@misc{dc5f061ebaaa66,
title = {Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification — arXiv:2610.34140},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34140},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f061ebaaa66; sha256 42d20ec1d148a95dea9bcf39105353b2c01af8169678019061be240364b8aa2b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34140. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
On million-node graphs, the memory wall arrives before the compute wall: a GNN that never fits in VRAM cannot deliver the all-node inference its accuracy promises. The standard remedy, pruning, has always been an accuracy tax - paid once and never refunded. DPR refuses this framing. Its central insight is that the mask that shrinks training can also scaffold recovery: one compact node set bounds both computations of graph learning, serving as the encoder's training graph and, at inference, as the anchor from which a sparse structure-aware decoder rebuilds every pruned node (double-layer sparsification). The order is inverted - prune for efficiency, then reconstruct for accuracy - and the tax is repaid: the deployed 30%-budget model trains in 1,450 MiB of peak memory on one 6 GB GPU and recovers 96.9% of its dense-reconstruction reference, beating a same-GPU rerun of the edge-sparsification baseline DSpar by +1.36 pp at 50.1% lower peak training memory; against the same-protocol full-batch no-prune encoder the deployed point pays a measured 2.64 pp accuracy tax for a 2.8x smaller training footprint. Pruning without reconstruction leaves the encoder at 0.378 within the same 40-epoch window (Fig. 4), and all-node serving runs 46x faster than sampling-based GraphSAGE, giving up approx. 5.4 pp of test accuracy. The framework scales to a 2.45M-node production graph at 6,285 MiB of peak training memory; extended variants (long-range context, external text features, a CAN-bus application) are reported as extensions and do not compete with the deployed method, and the 41.8%-budget M4 point, scored on a coarsened super-node graph with its own split, is reported separately rather than compared with the original-node baselines. DPR thus turns aggressive node pruning from an accuracy tax into a safe training accelerator for VRAM-limited all-node inference. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34140 — 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 2026-10-27T07:55:30.877Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).