Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation

• URL: http://arxiv.org/abs/2608.20804v2
• Date: Tue, 25 Aug 2026 15:39:45 GMT
• Title: Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation
• Abstract summary: FreqDiff is a Frequency-aware framework for TKG extrapolation.<n>FreqDiff formulates future object prediction as query-slot denoising.<n> Experiments on four public TKG benchmarks demonstrate that FreqDiff achieves state-of-the-art performance.
• Score: 14.39831625248832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HyFAD: Hybrid Time-Frequency Diffusion with Frequency-Aware Embedding for Time Series Imputation [10.212955864311589]
  We present textbfHyFAD, a time-frequency diffusion model for time series imputation.<n>It captures low-frequency global trends, while the frequency-domain diffusion process refines high-frequency spectral components.<n>Experiments on multiple benchmark datasets demonstrate that HyFAD achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-06-03T06:03:37Z)
• FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction [56.59654766009799]
  We present a novel empirical observation: user attention scores exhibit distinct spectral entropy distributions when conditioned on positive or negative target items.<n>We propose the Frequency-Enhanced Deep Interest Network (FEDIN) to capture latent periodic patterns in user interests.<n>FEDIN consistently outperforms state-of-the-art sequential recommendation baselines, demonstrating superior robustness against noise.
  arXiv  Detail & Related papers  (2026-05-03T05:50:36Z)
• Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation [16.301114199423044]
  Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence.<n>Negative-Aware Diffusion model for TKG Extrapolation (NADEx)<n>NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings.
  arXiv  Detail & Related papers  (2026-02-09T15:50:56Z)
• The Sound of Noise: Leveraging the Inductive Bias of Pre-trained Audio Transformers for Glitch Identification in LIGO [0.0]
  Transient noise artifacts, or glitches, limit the sensitivity of gravitational-wave (GW) interferometers.<n>Current glitch classification methods rely on supervised models trained from scratch using labeled datasets.<n>We present a novel cross-domain framework that treats GW strain data through the lens of audio processing.
  arXiv  Detail & Related papers  (2026-01-27T20:16:53Z)
• FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks [5.215187965365735]
  We show that models tend to fit low-frequency signals before high-frequency ones.<n>We propose the FreLE algorithm, which enhances model generalization through both explicit and implicit frequency regularization.
  arXiv  Detail & Related papers  (2025-10-29T03:22:51Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• FreDF: Learning to Forecast in the Frequency Domain [54.2091536822376]
  Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences.<n>We propose the Frequency-enhanced Direct Forecast (FreDF) which mitigates label autocorrelation by learning to forecast in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-04T08:23:41Z)
• SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecasting [29.55810183838032]
  SpecSTG is a novel spectral diffusion framework for traffic-temporal graph learning. It generates the Fourier representation of future time series, transforming the learning process into the spectral domain enriched with spatial information. Compared with state-of-the-arts, SpecSTG achieves up to 8% improvements on point estimations and up 0.78% improvements on quantifying future uncertainties.
  arXiv  Detail & Related papers  (2024-01-16T05:23:34Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping [51.698273019061645]
  SpecGrad adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders.
  arXiv  Detail & Related papers  (2022-03-31T02:08:27Z)
• PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior [103.00403682863427]
  We propose PriorGrad to improve the efficiency of the conditional diffusion model. We show that PriorGrad achieves a faster convergence leading to data and parameter efficiency and improved quality.
  arXiv  Detail & Related papers  (2021-06-11T14:04:03Z)
• Bayesian Reconstruction of Fourier Pairs [21.104218472462907]
  General literature fails to cater for missing observations and noise-corrupted data. Our aim is to address the lack of a principled treatment of data acquired indistinctly in the temporal and frequency domains. We show that the proposed model is able to perform joint time and frequency reconstruction of real-world audio, healthcare and astronomy signals.
  arXiv  Detail & Related papers  (2020-11-09T17:30:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.