Summary of Diversified and Adaptive Negative Sampling on Knowledge Graphs, by Ran Liu et al.
Diversified and Adaptive Negative Sampling on Knowledge Graphs
by Ran Liu, Zhongzhou Liu, Xiaoli Li, Hao Wu, Yuan Fang
First submitted to arxiv on: 10 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 proposed paper presents a generative adversarial approach called Diversified and Adaptive Negative Sampling (DANS) for knowledge graph embedding. Existing methods often ignore diversity and adaptiveness in their sampling process, which harms the informativeness of negative triplets used for training. The authors aim to address this issue by developing a two-way generator that generates more diverse negative triplets through two pathways and an adaptive mechanism that produces more fine-grained examples by localizing the global generator for different entities and relations. The proposed approach is evaluated on three benchmark knowledge graphs, demonstrating its effectiveness through quantitative and qualitative experiments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary DANS aims to improve negative triplet sampling in knowledge graph embedding. Current methods don’t consider diversity or adaptiveness, making them less effective. The authors suggest a new method that uses two generators to create diverse examples and an adaptive mechanism to make each sample more informative. This approach is tested on three real-world datasets, showing it performs better than existing methods. |
Keywords
» Artificial intelligence » Embedding » Knowledge graph
