Metraipolis › archive › dc_20fd6b703fa6

Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting — arXiv:2609.32143

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32143
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:52.791Z
SHA-256 of the archived text
1b92b93f4961306713885e3f66a8a5f5d4bbd0234f703dd3c7e5ec77bc156af0
Stable URL of this page
https://metraipolis.com/documento/dc_20fd6b703fa6

How to cite

Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting — arXiv:2609.32143 — arXiv (en), https://arxiv.org/abs/2609.32143 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20fd6b703fa6 (Metraipolis archive dc_20fd6b703fa6, sha256 1b92b93f4961306713885e3f66a8a5f5d4bbd0234f703dd3c7e5ec77bc156af0)
BibTeX
@misc{dc20fd6b703fa6,
  title = {Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting — arXiv:2609.32143},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32143},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20fd6b703fa6; sha256 1b92b93f4961306713885e3f66a8a5f5d4bbd0234f703dd3c7e5ec77bc156af0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32143. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains a challenge. Graph prompting offers a parameter-efficient alternative to fine-tuning, but existing methods largely treat pre-trained models as opaque feature extractors, ignoring their internal spectral structure. In this work, we identify a systematic phenomenon in pre-trained GNNs, which we term spectral bias: optimization during pre-training disproportionately aligns representations with directions associated with large singular values, leaving low-energy directions under-explored. We show that these underutilized directions can encode complementary information that is beneficial for downstream adaptation, especially under distribution shift. To leverage this insight, we propose Spectral Reverse Prompt (SRP), a prompting framework that rebalances the spectral contributions of frozen GNN encoders. SRP applies a learnable soft-thresholding mask in the spectral domain to down-weight dominant directions while amplifying weaker ones. In addition, SRP incorporates a null-space augmentation module that captures variation in directions with minimal activation under the frozen encoder. Extensive experiments across multiple benchmarks demonstrate that SRP achieves state-of-the-art performance with minimal additional parameters, highlighting that reweighting spectral components is a principled and effective strategy for parameter-efficient graph adaptation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2609.32143 — 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 2026-10-07T20:29:02.233Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).