Summary of Node-time Conditional Prompt Learning in Dynamic Graphs, by Xingtong Yu et al.
Node-Time Conditional Prompt Learning In Dynamic Graphs
by Xingtong Yu, Zhenghao Liu, Xinming Zhang, Yuan Fang
First submitted to arxiv on: 22 May 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 This paper proposes a novel framework called DYGPROMPT for pre-training and prompt learning on dynamic graphs. The authors aim to bridge the gap between link prediction and node classification tasks in dynamic graph modeling. They introduce dual prompts that address both task objectives and temporal variations across pre-training and downstream tasks. Additionally, they propose condition-nets to model evolving node-time patterns in downstream tasks. The framework is evaluated through extensive experiments on four public datasets. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating a new way for computers to understand how things change over time on the internet or social media. Right now, there are ways to train machines to predict who will be friends with whom online, but this doesn’t help us solve other important problems like figuring out what kind of person someone is based on their posts. The authors came up with a new approach that helps computers learn from these kinds of changes over time and uses it to improve how well they can do tasks like classifying people or objects. |
Keywords
» Artificial intelligence » Classification » Prompt