Summary of High-order Pooling For Graph Neural Networks with Tensor Decomposition, by Chenqing Hua and Guillaume Rabusseau and Jian Tang
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
by Chenqing Hua, Guillaume Rabusseau, Jian Tang
First submitted to arxiv on: 24 May 2022
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 Tensorized Graph Neural Network (tGNN) is a novel architecture that uses tensor decomposition to model high-order non-linear interactions among nodes in graph-structured data. Unlike existing GNNs, which rely on simple pooling operations, tGNN leverages the symmetric CP decomposition to efficiently parameterize permutation-invariant multilinear maps for modeling node interactions. This approach allows tGNN to capture more complex relationships between nodes, leading to improved performance on node and graph classification tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The new architecture uses tensor decomposition to model high-order non-linear interactions among nodes in graphs. This makes it better at understanding how nodes are connected and can make predictions about these connections. The research shows that this approach works well for both node and graph classification, and performs best on certain datasets compared to other methods. |
Keywords
* Artificial intelligence * Classification * Graph neural network
