Metraipolis › archive › dc_2467887c477d
Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation — arXiv:2608.20804
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20804
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:18:24.130Z
- SHA-256 of the archived text
3ff4552d87345773fafca0e77f511b8b7aabc71a73aacbb2255465f84267f0b3- Stable URL of this page
https://metraipolis.com/documento/dc_2467887c477d
How to cite
Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation — arXiv:2608.20804 — arXiv (en), https://arxiv.org/abs/2608.20804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2467887c477d (Metraipolis archive dc_2467887c477d, sha256 3ff4552d87345773fafca0e77f511b8b7aabc71a73aacbb2255465f84267f0b3)
BibTeX
@misc{dc2467887c477d,
title = {Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation — arXiv:2608.20804},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20804},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2467887c477d; sha256 3ff4552d87345773fafca0e77f511b8b7aabc71a73aacbb2255465f84267f0b3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal Knowledge Graph (TKG) extrapolation seeks to infer future facts from time-varying relational histories. Recent diffusion-based approaches improve uncertainty modeling through generative denoising, but their aggregated conditioning on subject histories may insufficiently distinguish query-specific evidence from non-salient historical facts, thereby diluting target-discriminative signals. To bridge this gap, we propose FreqDiff, a Frequency-aware Diffusion framework for TKG extrapolation. Specifically, FreqDiff formulates future object prediction as query-slot denoising and develops a dual-stream denoiser that integrates temporal dependency modeling with context-aware spectral calibration. The spectral branch synthesizes history-conditioned filters from learnable bases to adaptively re-calibrate denoising representations, while a frequency-domain regularizer is proposed to align the denoised target with the gold object in spectral space. Experiments on four public TKG benchmarks demonstrate that FreqDiff achieves state-of-the-art performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.20804 — 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 2026-10-18T10:17:37.583Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).