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

arXiv: https://arxiv.org/abs/2608.20804 · HTML: https://mlsanity.com/paper/2608.20804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [SimplE Embedding for Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1802.04868/) (2018)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (2017)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019)
- [Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks](https://mlsanity.com/paper/2012.08492/) (2020)
- [Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion](https://mlsanity.com/paper/2310.20453/) (2023)
- [Temporal Knowledge Graph Completion: A Survey](https://mlsanity.com/paper/2201.08236/) (2022)
- [TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation](https://mlsanity.com/paper/2010.01029/) (2020)
- [Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving](https://mlsanity.com/paper/2011.13611/) (2020)
- [Temporal Knowledge Graph Reasoning with Historical Contrastive Learning](https://mlsanity.com/paper/2211.10904/) (2022)
- [Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2405.14170/) (2024)
- [Language Through a Prism: A Spectral Approach for Multiscale Language Representations](https://mlsanity.com/paper/2011.04823/) (2020)
- [ChronoR: Rotation Based Temporal Knowledge Graph Embedding](https://mlsanity.com/paper/2103.10379/) (2021)
- [FFT-based Dynamic Token Mixer for Vision](https://mlsanity.com/paper/2303.03932/) (2023)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework](https://mlsanity.com/paper/2412.16557/) (2024)
- [Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation](https://mlsanity.com/paper/2511.06285/) (2025)
- [Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation](https://mlsanity.com/paper/2602.08815/) (2026)

## Abstract (arXiv)

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.