DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915107840196608 |
|---|---|
| author | Cao, Yukun Wang, Lisheng Huang, Luobin |
| author_facet | Cao, Yukun Wang, Lisheng Huang, Luobin |
| contents | Temporal knowledge graph (TKG) reasoning that infers future missing facts is an essential and challenging task. Predicting future events typically relies on closely related historical facts, yielding more accurate results for repetitive or periodic events. However, for future events with sparse historical interactions, the effectiveness of this method, which focuses on leveraging high-frequency historical information, diminishes. Recently, the capabilities of diffusion models in image generation have opened new opportunities for TKG reasoning. Therefore, we propose a graph node diffusion model with dual-domain periodic contrastive learning (DPCL-Diff). Graph node diffusion model (GNDiff) introduces noise into sparsely related events to simulate new events, generating high-quality data that better conforms to the actual distribution. This generative mechanism significantly enhances the model's ability to reason about new events. Additionally, the dual-domain periodic contrastive learning (DPCL) maps periodic and non-periodic event entities to Poincaré and Euclidean spaces, leveraging their characteristics to distinguish similar periodic events effectively. Experimental results on four public datasets demonstrate that DPCL-Diff significantly outperforms state-of-the-art TKG models in event prediction, demonstrating our approach's effectiveness. This study also investigates the combined effectiveness of GNDiff and DPCL in TKG tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01477 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning Cao, Yukun Wang, Lisheng Huang, Luobin Machine Learning Computation and Language Temporal knowledge graph (TKG) reasoning that infers future missing facts is an essential and challenging task. Predicting future events typically relies on closely related historical facts, yielding more accurate results for repetitive or periodic events. However, for future events with sparse historical interactions, the effectiveness of this method, which focuses on leveraging high-frequency historical information, diminishes. Recently, the capabilities of diffusion models in image generation have opened new opportunities for TKG reasoning. Therefore, we propose a graph node diffusion model with dual-domain periodic contrastive learning (DPCL-Diff). Graph node diffusion model (GNDiff) introduces noise into sparsely related events to simulate new events, generating high-quality data that better conforms to the actual distribution. This generative mechanism significantly enhances the model's ability to reason about new events. Additionally, the dual-domain periodic contrastive learning (DPCL) maps periodic and non-periodic event entities to Poincaré and Euclidean spaces, leveraging their characteristics to distinguish similar periodic events effectively. Experimental results on four public datasets demonstrate that DPCL-Diff significantly outperforms state-of-the-art TKG models in event prediction, demonstrating our approach's effectiveness. This study also investigates the combined effectiveness of GNDiff and DPCL in TKG tasks. |
| title | DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2411.01477 |