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

2026-08-21

AI Summary

针对时间知识图谱外推问题，提出频率感知扩散框架FreqDiff，通过上下文感知频谱校准和双流去噪器提高未来事实预测准确性。

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.

Problem

• Temporal Knowledge Graph
• extrapolation
• diffusion
• denoising
• uncertainty modeling

Innovation

• Frequency-aware Diffusion
• Temporal Knowledge Graph Extrapolation
• Dual-stream Denoiser
• Context-aware Spectral Calibration
• Spectral Domain Regularizer