Metraipolis › archive › dc_aed38ed1f10c
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation — arXiv:2609.00831
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00831
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:32:09.629Z
- SHA-256 of the archived text
2083aa36fbd785de1c1e89d6a694f6bfde26416b7787a9c34a5ca7e1855f8e6d- Stable URL of this page
https://metraipolis.com/documento/dc_aed38ed1f10c
How to cite
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation — arXiv:2609.00831 — arXiv (en), https://arxiv.org/abs/2609.00831 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aed38ed1f10c (Metraipolis archive dc_aed38ed1f10c, sha256 2083aa36fbd785de1c1e89d6a694f6bfde26416b7787a9c34a5ca7e1855f8e6d)
BibTeX
@misc{dcaed38ed1f10c,
title = {FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation — arXiv:2609.00831},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00831},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aed38ed1f10c; sha256 2083aa36fbd785de1c1e89d6a694f6bfde26416b7787a9c34a5ca7e1855f8e6d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00831. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduce Frequency-Domain Latent-attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at this https URL and this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Biomolecules (q-bio.BM). Pagina del lavoro: https://arxiv.org/abs/2609.00831 — 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 2026-10-17T06:15:12.648Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).