MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models to reduce computation complexity are limited in some areas . a new structure to reduce the computation complexity is proposed to accelerate Transformers . |
| Approach: | They propose a new feed forward network structure which splits matrix space to smaller space to reduce computation complexity. |
| Outcome: | The proposed model can achieve a faster speed and better accuracy on the long-range arena benchmark. |
Similar Papers
Mask Attention Networks: Rethinking and Strengthen Transformer (2021.naacl-main)
Copied to clipboard
Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang
| Challenge: | Existing research explores to enhance the two sublayers separately to improve the capability of Transformer for text representation. |
| Approach: | They propose to combine SAN and Feed-Forward Networks to create a dynamic mask attention network with a learnable mask matrix which can model localness adaptively. |
| Outcome: | The proposed model outperforms the original Transformer on translation and text summarization tasks. |
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space (2022.emnlp-main)
Copied to clipboard
| Challenge: | Fig. 1 shows how feed-forward network (FFN) layers are utilized to build LMs. |
| Approach: | They reverse-engineer the operation of feed-forward network layers to find out how they work . they show that each update can be decomposed to sub-updates corresponding to single parameter vectors . |
| Outcome: | The proposed model reduces the toxicity of GPT2 by almost 50% and improves computation efficiency with a simple early exit rule, saving 20% of computation on average. |
Speeding up Transformer Decoding via an Attention Refinement Network (2022.coling-1)
Copied to clipboard
| Challenge: | Extensive experiments on ten WMT machine translation tasks show that the proposed model yields an average of 1.35x faster (with almost no decrease in BLEU) |
| Approach: | They propose a weighted residual network which reconstructs attention by reusing the features across layers. |
| Outcome: | The proposed model is 1.35x faster than the state-of-the-art inference model on translation tasks compared to AAN and SAN models with fewer parameter numbers . |
TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Prior work has focused on treating subwords as basic units in developing such systems. |
| Approach: | They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences. |
| Outcome: | The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks. |
FFN Lens: How Transformers Divide Labor for Multilingual Tasks (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit strong performance on multilingual tasks, yet the process of constructing predictions in the target language remains under-explored. |
| Approach: | They propose a novel interpretability method focusing on the Feed-Forward Network (FFN) layers of Large Language Models. |
| Outcome: | The proposed interpretability method is based on the Feed-Forward Network (FFN) layer of Large Language Models. |
RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)
Copied to clipboard
Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu
| Challenge: | recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability. |
| Approach: | They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. |
| Outcome: | The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models. |
FNet: Mixing Tokens with Fourier Transforms (2022.naacl-main)
Copied to clipboard
| Challenge: | Using simple linear transformations, Transformer encoders can be sped up with limited accuracy costs by replacing the self-attention sublayers with simple linear mixing mechanisms. |
| Approach: | They propose to replace the self-attention sublayer with a linear transformation that "mixes" input tokens. |
| Outcome: | The proposed model outperforms the “efficient Transformers” on the GLUE benchmark at longer input lengths and on smaller models with a light memory footprint. |
ETC: Encoding Long and Structured Inputs in Transformers (2020.emnlp-main)
Copied to clipboard
Joshua Ainslie, Santiago Ontanon, Chris Alberti, Vaclav Cvicek, Zachary Fisher, Philip Pham, Anirudh Ravula, Sumit Sanghai, Qifan Wang, Li Yang
| Challenge: | Existing models for natural language processing (NLP) have been challenging to scale attention to longer inputs. |
| Approach: | They propose an extended Transformer construction architecture that scales attention to longer inputs by combining global-local attention with relative position encodings and a "Contrastive Predictive Coding" objective. |
| Outcome: | The proposed architecture scales attention to longer inputs and encodes structured inputs. |
How to Dissect a Muppet: The Structure of Transformer Embedding Spaces (2022.tacl-1)
Copied to clipboard
| Challenge: | Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm . a novel decomposition of Transformer output embeddables is demonstrated . |
| Approach: | They propose to decompose Transformer output embeddings into a sum of vector factors . they show multi-head attentions and feed-forwards are not equally useful in downstream applications . |
| Outcome: | The proposed method outperforms recurrent architectures on a wide variety of tasks. |
Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)
Copied to clipboard
Gongzheng Li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao
| Challenge: | Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application. |
| Approach: | They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model. |
| Outcome: | The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU. |