Papers › Protoformer: Embedding Prototypes for Transformers

Protoformer: Embedding Prototypes for Transformers

25 Jun 2022PAKDD 2022: Advances in Knowledge Discovery and Data Mining 2022 5arXiv:2206.12710archive 2025-07-28

Ashkan Farhangi, Ning Sui, Nan Hua, Haiyan Bai, Arthur Huang, Zhishan Guo

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.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ashfarhangi/Protoformer officialmentioned in paperpytorchGPL-3.0 report

EthanCoder24/Protofomer-NLP pytorch report

GitF82/NLP-Embeddings-Protoformer-Paper pytorch report

codelion/adaptive-classifier pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification General Classification Language Modelling Large Language Model Learning with noisy labels Self-Learning Sentiment Classification Text Classification

Datasets

Introduced by this paper, per the archive.

arXiv-10

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Text Classification	arXiv-10	Protoformer	Accuracy	0.794	#1 of 4	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Self-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections