Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Avital Oliver · Augustus Odena · Colin A Raffel · Ekin Dogus Cubuk · Ian Goodfellow

Thu Dec 6th 10:45 AM -- 12:45 PM @ Room 210 #95

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that SSL algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and performance can degrade substantially when the unlabeled dataset contains out-of-distribution examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.

Author Information

Avital Oliver (Google Brain)
Augustus Odena (Google Brain)
Colin A Raffel (Google Brain)

My research focuses on machine learning techniques for sequential data. I am currently a resident at Google Brain. I recently completed a PhD in Electrical Engineering at Columbia University In LabROSA, supervised by Dan Ellis. My thesis focused on learning-based methods for comparing sequences. In 2010, I received a Master's in Music, Science and Technology from Stanford University's CCRMA, supervised by Julius O. Smith III. I did my undergrad at Oberlin College, where I majored in Mathematics.

Dogus Cubuk (Google Brain)
Ian Goodfellow (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors