Summary of Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space, by Li Cai et al.
Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space
by Li Cai, Xin Mao, Zhihong Wang, Shangqing Zhao, Yuhao Zhou, Changxu Wu, Man Lan
First submitted to arxiv on: 2 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces a novel approach to temporal knowledge graph completion (TKGC) by utilizing quaternion representations within hypercomplex space. Unlike existing methods, this study focuses on capturing time-sensitive relations rather than time-aware entities. The authors model time-sensitive relations through time-aware rotation and periodic time translation, effectively capturing complex temporal variability. The proposed method is theoretically demonstrated to be capable of modeling symmetric, asymmetric, inverse, compositional, and evolutionary relation patterns. Experimental results on public datasets show that this approach achieves state-of-the-art performance in TKGC. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it easier for computers to understand how things are connected over time by using a new way to represent information called quaternion representations. Right now, computer scientists use different methods to fill in missing facts about what happened in the past or future, but this method is better because it focuses on how things change over time rather than just looking at specific times. The researchers used special math operations to make their method work and showed that it can handle lots of different types of connections between things. This means that computers can get even better at understanding complex patterns in data. |
Keywords
* Artificial intelligence * Knowledge graph * Translation
