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

arXiv:2608.20804v1 Announce Type: cross 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

• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
• Temporal Aware Pruning for Efficient Diffusion-based Video Generation
• WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

Source: arXiv cs.AI | 2026-08-24