paper-with-me

Papers

Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks

2024-03-19 · Bo-Ru Lu, Nikita Haduong, Chien-Yu Lin, Hao Cheng, Noah A. Smith, Mari Ostendorf

Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as GPT-4. We introduce a new configuration for encoder-decoder models that improves efficiency on structured output and decomposable tasks where multiple outputs are required for a single shared input. Our method, prompt-in-decoder (PiD), encodes the input once and decodes the output in parallel, boosting both training and inference efficiency by avoiding duplicate input encoding and increasing the operational intensity (ratio of numbers of arithmetic operation to memory access) of decoding process by sharing the input key-value cache. We achieve computation reduction that roughly scales with the number of subtasks, gaining up to 4.6x speed-up over state-of-the-art models for dialogue state tracking, summarization, and question-answering tasks, with comparable or better performance.

📄 PDF Abstract BibTeX arXiv:2403.13112

Code (1)

boru-roylu/encode-once-and-decode-in-parallel 공식 구현 pytorch

Tasks

DecoderDialogue State TrackingQuestion Answering

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models

2023-11-15 · Peng Tang, Pengkai Zhu, Tian Li, Srikar Appalaraju 외

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-r…

Decoder

Balancing Cost and Benefit with Tied-Multi Transformers

2020-02-20 · WS 2020 7 · Raj Dabre, Raphael Rubino, Atsushi Fujita

We propose and evaluate a novel procedure for training multiple Transformers with tied parameters which compresses multiple models into one enabling the dynamic choice of the number of encoder and decoder layers during d…

DecoderKnowledge DistillationMachine TranslationModel Compression+1

Rethinking Encoder-Decoder Flow Through Shared Structures

2025-01-24 · Frederik Laboyrie, Mehmet Kerim Yucel, Albert Saa-Garriga

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We int…

DecoderDepth Estimation

Graph-Aware Transformer: Is Attention All Graphs Need?

2020-06-09 · Sanghyun Yoo, Young-Seok Kim, Kang Hyun Lee, Kuhwan Jeong 외

Graphs are the natural data structure to represent relational and structural information in many domains. To cover the broad range of graph-data applications including graph classification as well as graph generation, it…

AllDecoderGraph ClassificationGraph Generation

Is Encoder-Decoder Redundant for Neural Machine Translation?

2022-10-21 · Yingbo Gao, Christian Herold, Zijian Yang, Hermann Ney

Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction a…

DecoderLanguage ModelingLanguage ModellingMachine Translation+2