← Back to all news
arXiv AI By Yanglei Gan, Peng He, Run Lin, Peiyuan Jiang, Yifan Wang, Qiao Liu

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

Read the original on arXiv AI →

The paper introduces FreqDiff, a Frequency-aware Diffusion framework designed to improve Temporal Knowledge Graph extrapolation. It frames future object prediction as a query-slot denoising task and employs a dual-stream denoiser that combines temporal dependency modeling with a context-aware spectral calibration branch. The spectral branch generates history-conditioned filters from learnable bases to recalibrate denoising representations, while a frequency-domain regularizer aligns the denoised output with the true target in spectral space, achieving state-of-the-art results on four public TKG benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 5

Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization

The paper introduces AdaSpecK, a spectral-Koopman framework designed for Temporal Domain Generalization (TDG). It combines spectral-regularized Koopman dynamics modeling to filter noise in latent space with a context-informed heterogeneous pattern extraction mechanism that uses target-conditioned attention and a learned router to summarize relevant past windows. Experiments on eight classification and regression benchmarks show that AdaSpecK achieves state‑of‑the‑art performance.

By Tengxue Zhang, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, Bin Yang
diffusionbenchmarks
More like this →
arXiv Machine Learning
4d ago

Time Will Tell: Harness Time to Denoise Collaborative Filtering

The paper introduces TintCF, a method that incorporates time-aware user and item embeddings to denoise collaborative filtering models. By reweighting the adjacency matrix (Tint‑A) or the loss function (Tint‑L), the approach leverages temporal patterns to identify and correct noisy or malicious interactions. Experiments on four real‑world datasets demonstrate that incorporating time information improves model robustness and performance.

By Xinyu He, Jose Sepulveda, Mostafa Rahmani, Alyssa Woo, Fei Wang, Hanghang Tong
rag
More like this →