Summary of One Model For One Graph: a New Perspective For Pretraining with Cross-domain Graphs, by Jingzhe Liu et al.
One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
by Jingzhe Liu, Haitao Mao, Zhikai Chen, Wenqi Fan, Mingxuan Ju, Tong Zhao, Neil Shah, Jiliang Tang
First submitted to arxiv on: 30 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
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 paper proposes a novel cross-domain pretraining framework for Graph Neural Networks (GNNs), allowing practitioners to infer which GNN model generalizes well across different domains. The framework, dubbed “one model for one graph,” overcomes the limitations of previous approaches by pretraining a bank of expert models, each corresponding to a specific dataset. When inferring to a new graph, gating functions choose a subset of experts to effectively integrate prior model knowledge while avoiding negative transfer. The proposed method demonstrates superiority on both link prediction and node classification tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps us understand how to make Graph Neural Networks (GNNs) work better across different types of networks. GNNs are powerful tools that can learn patterns in these networks, but they need special designs for each type of network, which can be hard. The researchers propose a new way to train GNNs that allows them to learn from many different networks and then use this knowledge to make good predictions on new networks. This is helpful because it makes it easier for people who aren’t experts in these areas to use GNNs. |
Keywords
» Artificial intelligence » Classification » Gnn » Pretraining
