paper-with-me

Papers

Interlocking Backpropagation: Improving depthwise model-parallelism

2020-10-08 · Aidan N. Gomez, Oscar Key, Kuba Perlin, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal

The number of parameters in state of the art neural networks has drastically increased in recent years. This surge of interest in large scale neural networks has motivated the development of new distributed training strategies enabling such models. One such strategy is model-parallel distributed training. Unfortunately, model-parallelism can suffer from poor resource utilisation, which leads to wasted resources. In this work, we improve upon recent developments in an idealised model-parallel optimisation setting: local learning. Motivated by poor resource utilisation in the global setting and poor task performance in the local setting, we introduce a class of intermediary strategies between local and global learning referred to as interlocking backpropagation. These strategies preserve many of the compute-efficiency advantages of local optimisation, while recovering much of the task performance achieved by global optimisation. We assess our strategies on both image classification ResNets and Transformer language models, finding that our strategy consistently out-performs local learning in terms of task performance, and out-performs global learning in training efficiency.

📄 PDF Abstract BibTeX arXiv:2010.04116

Code (1)

oscarkey/interlocking-backprop 공식 구현 pytorch

Tasks

image-classificationImage Classificationmodel

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
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…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Asynchronous Stochastic Gradient Descent with Decoupled Backpropagation and Layer-Wise Updates

2024-10-08 · Cabrel Teguemne Fokam, Khaleelulla Khan Nazeer, Lukas König, David Kappel 외

The increasing size of deep learning models has made distributed training across multiple devices essential. However, current methods such as distributed data-parallel training suffer from large communication and synchro…

Distributed Computing

Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions

2021-04-29 · Tse-Wei Chen, Wei Tao, Deyu Wang, Dongchao Wen 외

In order to handle modern convolutional neural networks (CNNs) efficiently, a hardware architecture of CNN inference accelerator is proposed to handle depthwise convolutions and regular convolutions, which are both essen…

Face Detectionimage-classificationImage Classification

Parallel Training of Deep Networks with Local Updates

2020-12-07 · Michael Laskin, Luke Metz, Seth Nabarro, Mark Saroufim 외

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compu…

Interlocking-free Selective Rationalization Through Genetic-based Learning

2024-12-13 · Federico Ruggeri, Gaetano Signorelli

A popular end-to-end architecture for selective rationalization is the select-then-predict pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative system suffers from suboptimal equi…

2BP: 2-Stage Backpropagation

2024-05-28 · Christopher Rae, Joseph K. L. Lee, James Richings

As Deep Neural Networks (DNNs) grow in size and complexity, they often exceed the memory capacity of a single accelerator, necessitating the sharding of model parameters across multiple accelerators. Pipeline parallelism…