Protoformer: Embedding Prototypes for Transformers

Code

• github.com/ashfarhangi/Protoformer
  OfficialIn paperpytorch★ 28
• github.com/EthanCoder24/Protofomer-NLP
  pytorch★ 7
• github.com/GitF82/NLP-Embeddings-Protoformer-Paper
  pytorch★ 3
• github.com/codelion/adaptive-classifier/blob/main/src/adaptive_classifier/memory.py
  pytorch★ 0

Abstract

Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning framework for Transformers that can leverage problematic samples for text classification. Protoformer features a selection mechanism for embedding samples that allows us to efficiently extract and utilize anomalies prototypes and difficult class prototypes. We demonstrated such capabilities on datasets with diverse textual structures (e.g., Twitter, IMDB, ArXiv). We also applied the framework to several models. The results indicate that Protoformer can improve current Transformers in various empirical settings.

Tasks

Benchmark Results

Reproductions