ACL Findings2024
Predicting the Unpredictable: Uncertainty-Aware Reasoning over Temporal Knowledge Graphs via Diffusion Process
Yuxiang Cai, Qiao Liu, Yanglei Gan, Changlin Li, Xueyi Liu, Run Lin, Da Luo, Jiaye Yang
Abstract
Temporal Knowledge Graph (TKG) reasoning seeks to predict future incomplete facts leveraging historical data. While existing approaches have shown effectiveness in addressing the task through various perspectives, such as graph learning and logic rules, they are limited in capturing the indeterminacy in future events, particularly in the case of rare/unseen facts. To tackle the highlighted issues, we introduce a novel approach by conceptualizing TKG reasoning as a sequence denoising process for future facts, namely DiffuTKG. Concretely, we first encodes the historical events as the conditional sequence. Then we gradually introduce Gaussian noise to corrupt target facts during the forward process and then employ a transformerbased conditional denoiser to restore them in the reverse phase. Moreover, we introduce an uncertainty regularization loss to mitigate the risk of prediction biases by favoring frequent scenarios over rare/unseen facts. Empirical results on four real-world datasets show that Dif-fuTKG outperforms state-of-the-art methods across multiple evaluation metrics 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting cites Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- AnRe: Analogical Replay for Temporal Knowledge Graph Forecasting cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting cites Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning cites Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning cites High-Resolution Image Synthesis with Latent Diffusion Models
- A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning cites Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs
- A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers4
- A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph ReasoningZhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu WanACL 2025 · 4 citations
- AnRe: Analogical Replay for Temporal Knowledge Graph ForecastingGuo Tang, Zheng Chu, Wenxiang Zheng, Junjia Xiang et al.ACL 2025 · 3 citations
- Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion ModelsHaoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng et al.KDD 2026 · 1 citation
- Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph ForecastingSiyuan Li, Yunjia Wu, Yiyong Xiao, Pingyang Huang et al.ACL 2026
Builds on20
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Energy-based Out-of-distribution DetectionWeitang Liu, Xiaoyun Wang, John D. Owens, Yixuan LiNeurIPS 2020 · 2,213 citations
- Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge GraphsWoojeong Jin, Meng Qu, Xisen Jin, Xiang RenEMNLP 2020 · 353 citations
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation LearningZixuan Li, Xiaolong Jin, Wei Li, Saiping Guan et al.SIGIR 2021 · 345 citations
Related papers
- DLTKG: Denoising Logic-based Temporal Knowledge Graph ReasoningXiaoke Wang, Fu Zhang, Jingwei Cheng, Yiwen Chi et al.EMNLP Findings 2025 · 2 citations
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph ForecastingHaohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han et al.EMNLP 2021 · 164 citations
- Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge GraphsHaohai Sun, Shangyi Geng, Jialun Zhong, Han Hu et al.EMNLP 2022 · 46 citations
- DPCL-Diff:Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive LearningYukun Cao, Lisheng Wang, Luobin HuangAAAI 2025 · 5 citations
- A Unified Temporal Knowledge Graph Reasoning Model Towards Interpolation and ExtrapolationKai Chen, Ye Wang, Yitong Li, Aiping Li et al.ACL 2024 · 4 citations
