# Less is More! A slim architecture for optimal language translation

arXiv: https://arxiv.org/abs/2305.10991 · HTML: https://mlsanity.com/paper/2305.10991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [DeepNet: Scaling Transformers to 1,000 Layers](https://mlsanity.com/paper/2203.00555/) (2022)
- [Scatterbrain: Unifying Sparse and Low-rank Attention Approximation](https://mlsanity.com/paper/2110.15343/) (2021)
- [Gated Feedback Recurrent Neural Networks](https://mlsanity.com/paper/1502.02367/) (2015)
- [Compressing deep neural networks by matrix product operators](https://mlsanity.com/paper/1904.06194/) (2019)
- [Sub-Linear Memory: How to Make Performers SLiM](https://mlsanity.com/paper/2012.11346/) (2020)

## Abstract (arXiv)

The softmax attention mechanism has emerged as a noteworthy development in the field of Artificial Intelligence research, building on the successes of Transformer-based architectures. However, their ever increasing sizes necessitate ever increasing computational memory, that limits their usage. We propose KgV, a sigmoid gating mechanism that, in conjunction with softmax attention, significantly boosts performance without increasing architecture size. To amend the size requirements, we leverage Tensor Chains to identify and prune the excess parameters. We find that such excess resides primarily within the embedding layer, and not in the output linear layer. To further improve embedding and significantly reduce parameters, we introduce H-SoftPOS, a hierarchical embedding layer which simultaneously enhances performance. Remarkably, on the WMT14 English-German validation set, our approach yields a threefold reduction in perplexity, surpassing the current state-of-the-art, while reducing parameter counts also by a factor of 3. When we further reduce the number of parameters up to sevenfold, we can still achieve a 21% decrease in perplexity with respect to the baseline Transformer. To understand generalization capabilities, we conduct experiments on the 7 language pairs of the WMT17 dataset. Our method outperforms existing techniques in terms of test loss while simultaneously halving the number of parameters. Moreover, we observe a 70 times reduction in variance with respect to the prior state-of-the-art. In conclusion, our proposed method yields significant improvements in performance and much lower memory cost. We call the resulting architecture Anthe.