Methods › Natural Language Processing › Transformers › Funnel Transformer

Funnel Transformer

2 papers tagged archive 2025-07-28

Introduced by Zihang Dai et al. in Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Funnel Transformer is a type of Transformer that gradually compresses the sequence of hidden states to a shorter one and hence reduces the computation cost. By re-investing the saved FLOPs from length reduction in constructing a deeper or wider model, the model capacity is further improved. In addition, to perform token-level predictions as required by common pretraining objectives, Funnel-transformer is able to recover a deep representation for each token from the reduced hidden sequence via a decoder.

The proposed model keeps the same overall skeleton of interleaved S-Attn and P-FFN sub-modules wrapped by residual connection and layer normalization. But differently, to achieve representation compression and computation reduction, THE model employs an encoder that gradually reduces the sequence length of the hidden states as the layer gets deeper. In addition, for tasks involving per-token predictions like pretraining, a simple decoder is used to reconstruct a full sequence of token-level representations from the compressed encoder output. Compression is achieved via a pooling operation,

PaperSource

Papers archive 2025-07-28

2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Computational Efficiency1
Decoder1
Reading Comprehension1
Text Classification1

Usage over time archive 2025-07-28

Papers per year tagged with Funnel Transformer: 2020 to 2025, peak 1 1 0 2020: 1 paper 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 0 papers 2023 2024: 0 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

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