paper-with-me

Papers

Block-State Transformers

2023-06-15 · NeurIPS 2023 11

State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic runtime complexity. Originally designed for continuous signals, SSMs have shown superior performance on a plethora of tasks, in vision and audio; however, SSMs still lag Transformer performance in Language Modeling tasks. In this work, we propose a hybrid layer named Block-State Transformer (BST), that internally combines an SSM sublayer for long-range contextualization, and a Block Transformer sublayer for short-term representation of sequences. We study three different, and completely parallelizable, variants that integrate SSMs and block-wise attention. We show that our model outperforms similar Transformer-based architectures on language modeling perplexity and generalizes to longer sequences. In addition, the Block-State Transformer demonstrates more than tenfold increase in speed at the layer level compared to the Block-Recurrent Transformer when model parallelization is employed.

📄 PDF Abstract BibTeX arXiv:2306.09539

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingState Space Models

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Ring Attention with Blockwise Transformers for Near-Infinite Context

2023-10-03 · Hao liu, Matei Zaharia, Pieter Abbeel

Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands imposed by Transformers …

Language ModelingLanguage Modelling

Transformers Meet Small Datasets

2022-11-09 · IEEE Access 2022 11 · Ran Shao, Xiao-Jun Bi

The research and application areas of transformers have been extensively enlarged due to the success of vision transformers (ViTs). However, due to the lack of local content acquisition capabilities, the pure transformer…

Classification

Why Transformers Need Adam: A Hessian Perspective

2024-02-26 · Yushun Zhang, Congliang Chen, Tian Ding, Ziniu Li 외

SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Transformers are "heterogeneous": the Hessian…

Blockwise Parallel Transformers for Large Context Models

2023-09-21 · NeurIPS 2023 11

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the sel…

Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models

2020-09-18 · Jihyeon Roh, Huiseong Gim, Soo-Young Lee

We report a GPT-based multi-sentence language model for dialogue generation and document understanding. First, we propose a hierarchical GPT which consists of three blocks, i.e., a sentence encoding block, a sentence gen…

DecoderDialogue Generationdocument understandingLanguage Modeling+4