Summary of Bootstrap Latents Of Nodes and Neighbors For Graph Self-supervised Learning, by Yunhui Liu et al.
Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
by Yunhui Liu, Huaisong Zhang, Tieke He, Tao Zheng, Jianhua Zhao
First submitted to arxiv on: 9 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 In this paper, researchers propose a new approach to graph self-supervised learning that improves upon existing methods by incorporating positive pairs into the training process. The method, called cross-attention-based node clustering, uses a cross-attention module to predict the supportiveness score of neighboring nodes with respect to an anchor node, and encodes this information into the training objective. This approach mitigates class collision from negative and noisy positive samples, leading to enhanced intra-class compactness and state-of-the-art performance on five benchmark datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores new ways to learn graph representations without using labels. The main idea is to use neighboring nodes as positive examples, which helps the model learn more about each node’s label. To do this, the authors introduce a special module that looks at how well each neighbor supports the anchor node’s label. This information is then used to train the model. By doing so, they can avoid some of the issues that come with using negative examples and achieve better results. |
Keywords
* Artificial intelligence * Clustering * Cross attention * Self supervised
