arXiv AI

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

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.

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

diffusion benchmarks

arXiv AI

Sep 30

HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

arXiv:2609.36559v1 Announce Type: cross Abstract: Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early...

By Yansong Liu, Rui Liu, Yuan Zuo, Hongwei Zhao, Da Fu, Fuwei Zhang, Fuzhen Zhuang, Yong Chen, Zhe Li

fine-tuning efficiency benchmarks

arXiv AI

Aug 24

Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation

arXiv:2608.21243v1 Announce Type: cross Abstract: Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equally informative. Real logs combi...

By Zichun Jin, Zihan Zhou, Yinan Liu, Bin Wang, Xiaochun Yang

safety

arXiv Machine Learning

Jun 16

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.

By Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang

llms diffusion fine-tuning

arXiv AI

Jul 14

GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

arXiv:2607. 10197v1 Announce Type: new Abstract: Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations.

By Jiaxin Pan, Osama Mohammed, Daniel Hern\'andez, Steffen Staab

benchmarks

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

arXiv AI

Aug 25

Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation

arXiv:2608.23400v1 Announce Type: cross Abstract: Discrete Diffusion Models (DDMs) have recently been introduced to recommendation systems, modeling user history as a token generation process via ite...

By Jiaqi Wang, Tianying Liu, Heng Chang, Jihong Guan, Wengen Li, Shuigeng Zhou

diffusion benchmarks

arXiv Machine Learning

Sep 29

More Sensors Only One Field: Rethinking Continual Spatio-Temporal Forecasting

The paper introduces STFO (Spatio-Temporal Field Operator), a method for continual spatio‑temporal forecasting that decouples forecasting representations from specific sensor layouts. By normalizing coordinate‑based aggregation onto a fixed latent grid and using a spectral descriptor to adapt to process drift, STFO can reuse learned spatial maps across varying sensor configurations. Experiments on PEMS‑Stream, CA‑Stream, and AIR‑Stream show that STFO‑Large improves average MAE by 8.4% over DOL on PEMS‑Stream and 4.7% on CA‑Stream.

By Lewei Xie, Haoyu Zhang, Jiajun Zhou, Yulong Chen, Guanxing Chen, Yu-An Huang, Hau-San Wong, Yifan Zhang, Zhi-An Huang

benchmarks

arXiv AI

Jun 9

DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Forecasting in Urban Transportation Systems

arXiv:2606. 07695v1 Announce Type: cross Abstract: Multi-Modality Spatio-Temporal Forecasting (MoSTF) extends traditional spatio-temporal forecasting by incorporating diverse traffic modalities.

By Yongchao Li, Yang Li, Zhuoxuan Li, Jun Chen, Chu Zhang, Jinde Cao, Leszek Rutkowski

benchmarks

arXiv AI

Jun 15

AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

arXiv:2605. 07121v2 Announce Type: replace Abstract: Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events.

By Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn

arXiv Machine Learning

Jul 31

Dynamic Spectral Filtering for Temporal Graph Learning: Learning Evolving Propagation Operators

arXiv:2607. 27891v1 Announce Type: cross Abstract: Temporal graph learning is commonly organized around the evolution of node states or the encoding of interaction histories.

By Yan Kong

benchmarks safety

arXiv Machine Learning

Aug 12

ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models

arXiv:2608. 10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what happens while treating when it happens as a secondary concern.

By Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji, Francesco Bronzino

llms

Related stories