Multi Label Zero Shot Classification with Graphs

Hi everyone! This is my first post! I’m excited to be here!

I’m currently exploring multi-label text classification and I was hoping to get some advice.

Specifically, I’m interested in using over 700 abstracts to classify more than 1100 labels. However, the predicted labels have a hierarchical structure, with some labels being subcategories of others. For instance, “Libraries” is a parent label, while “Public libraries” and “Reference libraries” are child labels under the “Libraries” category.

I’m facing a few challenges and I could really use some input.

Problem 1:
There isn’t enough training data available for each label.

Problem 2:
There are simply too many labels to handle, especially considering the hierarchy. On top of that, the hierarchy itself may evolve over time, which is another issue I need to address.

Problem 3:
Lastly, I’m not sure how to input the hierarchy into a pre-trained language model for sequence classification.

I’m wondering if this should be approached as a graph neural network problem? Perhaps I could consider the labels as a directed graph and somehow view the text-to-node similarity? I’m not entirely sure, and I’d love to hear your thoughts.

My end goal is to assist cataloguers in the library domain with indexing books.
Any advice would be greatly appreciated!