Summary of Representation Learning For Frequent Subgraph Mining, by Rex Ying et al.
Representation Learning for Frequent Subgraph Mining
by Rex Ying, Tianyu Fu, Andrew Wang, Jiaxuan You, Yu Wang, Jure Leskovec
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 The paper presents Subgraph Pattern Miner (SPMiner), a novel neural approach for finding frequent subgraphs in large target graphs. SPMiner combines graph neural networks, order embedding space, and an efficient search strategy to identify network subgraph patterns that appear most frequently in the target graph. The approach first decomposes the target graph into many overlapping subgraphs and then encodes each subgraph into an order embedding space. Next, SPMiner uses a monotonic walk in the order embedding space to identify frequent motifs. Compared to existing approaches, SPMiner is more accurate, faster, and more scalable. It can accurately identify most frequent 5- and 6-node motifs while being 100x faster than exact enumeration methods. Additionally, SPMiner can reliably identify frequent 10-node motifs, which is beyond the size limit of exact enumeration approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine trying to find patterns in a big network with many nodes and edges. Identifying these patterns, called “network motifs,” helps us understand how the network works. But finding these patterns can be very hard because there are so many possible combinations. A new approach called Subgraph Pattern Miner (SPMiner) makes it easier by breaking down the big network into smaller parts and then searching for patterns in those parts. SPMiner is faster, more accurate, and better than other methods at finding patterns in big networks. |
Keywords
* Artificial intelligence * Embedding space
