DeepAI AI Chat
Log In Sign Up

Learning Compact Features via In-Training Representation Alignment

by   Xin Li, et al.
Wayne State University

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of the feature extractor (i.e., last hidden layer) and a linear classifier (i.e., output layer) that are trained jointly with stochastic gradient descent (SGD) on the loss function (e.g., cross-entropy). In each epoch, the true gradient of the loss function is estimated using a mini-batch sampled from the training set and model parameters are then updated with the mini-batch gradients. Although the latter provides an unbiased estimation of the former, they are subject to substantial variances derived from the size and number of sampled mini-batches, leading to noisy and jumpy updates. To stabilize such undesirable variance in estimating the true gradients, we propose In-Training Representation Alignment (ITRA) that explicitly aligns feature distributions of two different mini-batches with a matching loss in the SGD training process. We also provide a rigorous analysis of the desirable effects of the matching loss on feature representation learning: (1) extracting compact feature representation; (2) reducing over-adaption on mini-batches via an adaptive weighting mechanism; and (3) accommodating to multi-modalities. Finally, we conduct large-scale experiments on both image and text classifications to demonstrate its superior performance to the strong baselines.


page 1

page 2

page 3

page 4


Improve SGD Training via Aligning Mini-batches

Deep neural networks (DNNs) for supervised learning can be viewed as a p...

Improve SGD Training via Aligning Min-batches

Deep neural networks (DNNs) for supervised learning can be viewed as a p...

RECAL: Reuse of Established CNN classifer Apropos unsupervised Learning paradigm

Recently, clustering with deep network framework has attracted attention...

EE-Grad: Exploration and Exploitation for Cost-Efficient Mini-Batch SGD

We present a generic framework for trading off fidelity and cost in comp...

A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks

We present a novel algorithm for training deep neural networks in superv...

CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data

Given a large unlabeled set of images, how to efficiently and effectivel...

Meta-Learning Mini-Batch Risk Functionals

Supervised learning typically optimizes the expected value risk function...