Metraipolis › archive › dc_cded8dfa4758

Node-wise Feature Encoding for Neural Performance Prediction — arXiv:2608.27794

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27794
License (as archived)
CC0-1.0
Archived
2026-10-17T11:06:26.893Z
SHA-256 of the archived text
7b38b624419e43609b2d24033aa5fe7d7866e7b37328317f718cb173133d8c24
Stable URL of this page
https://metraipolis.com/documento/dc_cded8dfa4758

How to cite

Node-wise Feature Encoding for Neural Performance Prediction — arXiv:2608.27794 — arXiv (en), https://arxiv.org/abs/2608.27794 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cded8dfa4758 (Metraipolis archive dc_cded8dfa4758, sha256 7b38b624419e43609b2d24033aa5fe7d7866e7b37328317f718cb173133d8c24)
BibTeX
@misc{dccded8dfa4758,
  title = {Node-wise Feature Encoding for Neural Performance Prediction — arXiv:2608.27794},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27794},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cded8dfa4758; sha256 7b38b624419e43609b2d24033aa5fe7d7866e7b37328317f718cb173133d8c24},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27794. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As neural networks are increasingly deployed on resource constrained edge devices, accurate prediction of latency and energy is critical for efficient neural architecture search. Existing GNN and transformer based predictors achieve strong results but largely ignore node-level computational cost, limiting their ability to model performance critical operations. To address this, we introduce FeatureFormer, a neural performance predictor that incorporates explicit node-wise encodings of FLOPs, parameter counts, and memory proxies within a gated graph attention architecture. We also present NNEQ, a new large-scale energy consumption dataset that enables unified evaluation of latency and energy prediction. Extensive experiments demonstrate that FeatureFormer achieves state-of-the-art performance across both metrics, including challenging out-of-domain settings. Finally, we show that the proposed encoding is broadly applicable and consistently improves existing predictors with negligible overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.27794 — 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 2026-10-17T10:50:25.778Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).