Papers › Subformer: A Parameter Reduced Transformer

Subformer: A Parameter Reduced Transformer

1 Jan 2021archive 2025-07-28

Machel Reid, Edison Marrese-Taylor, Yutaka Matsuo

The advent of the Transformer can arguably be described as a driving force behind many of the recent advances in natural language processing. However, despite their sizeable performance improvements, as recently shown, the model is severely over-parameterized, being parameter inefficient and computationally expensive to train. Inspired by the success of parameter-sharing in pre-trained deep contextualized word representation encoders, we explore parameter-sharing methods in Transformers, with a specific focus on encoder-decoder models for sequence-to-sequence tasks such as Machine Translation. We perform an analysis of different parameter sharing/reduction methods and develop the Subformer, a parameter efficient Transformer-based model which combines the newly proposed Sandwich-style parameter sharing technique and self-attentive embedding factorization (SAFE). Experiments on machine translation, abstractive summarization, and language modeling show that the Subformer can outperform the Transformer even when using significantly fewer parameters. On the WMT'14 English-German test set, we show we can perform equally well, and even sometimes outperform (+0.1 BLEU score) the Transformer-base model while using 40% less parameters. We also perform equally well as Transformer-big with 40% less parameters and outperform the model by 0.7 BLEU with 12M less parameters. We also outperform the standard Transformer-XL model, achieving a significant 3.6 lower perplexity with 37% fewer parameters.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Abstractive Text SummarizationDecoderLanguage ModelingLanguage ModellingMachine TranslationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail Subformer-base ROUGE-1 40.9 #37 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Subformer-base ROUGE-2 18.3 #37 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail Subformer-base ROUGE-L 37.7 #37 of 53 Archive leaderboard report
Language Modelling WikiText-103 Subformer Number of params 96M #42 of 89 Archive leaderboard report
Language Modelling WikiText-103 Subformer Test perplexity 20.39 #42 of 89 Archive leaderboard report
Machine Translation WMT2014 English-German Subformer-xlarge BLEU score 29.3 #26 of 91 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

Absolute Position EncodingsAdamAdaptive Input RepresentationsAdaptive SoftmaxAttentionBPECosine AnnealingDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxSubformerTransformerTransformer-XLVariational Dropout

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