Summary of Gaprotonet: a Multi-head Graph Attention-based Prototypical Network For Interpretable Text Classification, by Ximing Wen et al.
GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification
by Ximing Wen, Wenjuan Tan, Rosina O. Weber
First submitted to arxiv on: 20 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- 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 A novel white-box Multi-head Graph Attention-based Prototypical Network, called GAProtoNet, is introduced to explain the decisions of text classification models built with Language Model (LM) encoders. The approach utilizes multi-head graph attention to selectively construct edges between the input node and prototype nodes to learn an interpretable prototypical representation. This allows the model’s choices to be transparently explained by the attention weights and the prototypes projected into the closest matching training examples. Experimental results on multiple public datasets show that GAProtoNet achieves superior results without sacrificing the accuracy of the original black-box LMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is found to make text classification models more understandable. This is done by creating a network called GAProtoNet, which uses graph attention to connect input data and prototypes in a way that shows how decisions are made. This makes it possible to explain why the model chose certain words or phrases. The approach is tested on several datasets and shown to be effective without losing accuracy. |
Keywords
» Artificial intelligence » Attention » Language model » Text classification
