Summary of Prompt Learning on Temporal Interaction Graphs, by Xi Chen et al.
Prompt Learning on Temporal Interaction Graphs
by Xi Chen, Siwei Zhang, Yun Xiong, Xixi Wu, Jiawei Zhang, Xiangguo Sun, Yao Zhang, Feng Zhao, Yulin Kang
First submitted to arxiv on: 9 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); Social and Information Networks (cs.SI)
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 Temporal Interaction Graphs (TIGs) are a crucial representation of real-world systems. To advance pre-training on TIGs, researchers have developed various models. However, these models still face two significant hurdles in their “pre-train, predict” approach. Firstly, the temporal disparity between training and inference data limits their applicability for predicting future events on dynamically evolving datasets. Secondly, the semantic divergence between pretext and downstream tasks impedes their practical applications, as they struggle to align with their learning and prediction capabilities across diverse scenarios. To address these challenges, this paper proposes [insert model name(s) or method(s)] that leverages [specific technique or architecture]. This innovative approach aims to bridge the gaps between pre-training and downstream predictions, ultimately enabling more effective representation learning on TIGs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a graph that shows how things change over time. Researchers want to make this graph better by training machines to understand it. They’ve tried different methods, but they still have two big problems. First, the data used for training and making predictions doesn’t match up well. This makes it hard to predict what will happen in the future when new data comes in. Second, the tasks they’re trying to solve are very different from each other. This means machines struggle to learn from one task and apply that learning to another task. To fix these issues, scientists propose a new way of training machines using [specific technique or architecture]. This new approach hopes to make it easier for machines to learn from graphs like this and make better predictions. |
Keywords
* Artificial intelligence * Inference * Representation learning
