0

Association rule mining is considered to be an old technique of AI. Rules are mined on statistical support. How can deep learning be applied to this? What are approaches for structured data (in a graph format like XML)?

XML documents are structured by tags.

My goal is to extract a rule that says that tag x is often combined with tag y and z. Then, I later want to apply these rules and if a tag y and z is found, the tag x is inserted or recommended to be inserted.

user3352632
  • 449
  • 3
  • 7
  • Please clarify what would be the goal of this. – Erwan May 18 '22 at 09:28
  • @Erwan please find my goal in the description above. – user3352632 May 18 '22 at 11:17
  • Sorry, it's still not really clear: what kind of data, what are these fragments? what role would deep learning play in this scenario? – Erwan May 18 '22 at 11:48
  • @Erwan sorry, fragement could be a tag, a part of the XML document. The rules should be learned by deep learning ... is this possible? – user3352632 May 18 '22 at 12:01
  • Oh, so you would like to use DL instead of association rule mining? But are you sure there's an advantage doing this? It would be much more complex but would it really solve any problem or give better results than rule mining? Also it would require more data, probably. – Erwan May 18 '22 at 12:21
  • @Erwan that is the research question I want to investigate but I am not aware of the current SOTA rule mining approaches with deep learning. Can you help me? – user3352632 May 18 '22 at 16:30
  • This is not my area of expertise, I can only help you with asking a good question on the site ;) As far as I know it's not a standard task so it's unlikely that people would know about this here. Usually in research you should start with identifying relevant literature, apparently there are [a few papers related to your question](https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=association+rules+mining+neural+network). – Erwan May 18 '22 at 16:51

0 Answers0