Summary of Vn Network: Embedding Newly Emerging Entities with Virtual Neighbors, by Yongquan He and Zihan Wang and Peng Zhang and Zhaopeng Tu and Zhaochun Ren
VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
by Yongquan He, Zihan Wang, Peng Zhang, Zhaopeng Tu, Zhaochun Ren
First submitted to arxiv on: 21 Feb 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 This paper proposes a novel framework called Virtual Neighbor (VN) network to address three key challenges in embedding entities and relations into continuous vector spaces. The VN network aims to reduce neighbor sparsity, capture complex patterns, and iteratively learn between the embedding method and virtual neighbor prediction. By introducing virtual neighbors inferred by rules and assigning soft labels, the model can handle newly emerging entities without requiring retraining. The proposed framework is evaluated on two knowledge graph completion tasks, outperforming state-of-the-art baselines. Additionally, results show that VN network is robust to the neighbor sparsity problem. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a way to understand relationships between things, like people or objects. Right now, it takes a long time to learn about new things if we already know some related things. This paper proposes a new method called Virtual Neighbor (VN) network that helps with this problem. It uses rules to guess what might be connected to something we don’t know much about yet. The VN network also looks at more than just the closest connections, and it learns as it goes along. This makes it good at understanding complex relationships between things. |
Keywords
* Artificial intelligence * Embedding * Knowledge graph
