Summary of Pown: Prototypical Open-world Node Classification, by Marcel Hoffmann et al.
POWN: Prototypical Open-World Node Classification
by Marcel Hoffmann, Lukas Galke, Ansgar Scherp
First submitted to arxiv on: 14 Jun 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 The proposed paper addresses the issue of true open-world semi-supervised node classification in graphs, where nodes belong to known or new classes. The existing methods detect and reject new classes but fail to distinguish between different new classes. To solve this problem, a novel end-to-end approach called Prototypical Open-World Learning for Node Classification (POWN) is introduced. POWN combines graph semi-supervised learning, self-supervised learning, and pseudo-labeling to learn prototype representations of new classes in a zero-shot way. The paper demonstrates the effectiveness of POWN on benchmark datasets, outperforming baselines by up to 20% accuracy on small and up to 30% on large datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about solving a problem with classifying nodes in graphs that are either known or new. The current methods can detect when there’s a new class, but they don’t know what kind of new class it is. To fix this, the authors introduce a new way to learn called Prototypical Open-World Learning for Node Classification (POWN). POWN uses different techniques like graph learning and pseudo-labeling to figure out what these new classes are. The results show that POWN works better than other methods on certain datasets. |
Keywords
» Artificial intelligence » Classification » Self supervised » Semi supervised » Zero shot
