Smooth Neighbors on Teacher Graphs for Semi-supervised Learning

11/01/2017
by   Yucen Luo, et al.
0

The paper proposes an inductive semi-supervised learning method, called Smooth Neighbors on Teacher Graphs (SNTG). At each iteration during training, a graph is dynamically constructed based on predictions of the teacher model, i.e., the implicit self-ensemble of models. Then the graph serves as a similarity measure with respect to which the representations of "similar" neighboring points are learned to be smooth on the low dimensional manifold. We achieve state-of-the-art results on semi-supervised learning benchmarks. The error rates are 9.89 labels, respectively. In particular, the improvements are significant when the labels are scarce. For non-augmented MNIST with only 20 labels, the error rate is reduced from previous 4.81 noisy supervision and shows robustness to incorrect labels.

READ FULL TEXT
research
10/12/2021

Couple Learning: Mean Teacher method with pseudo-labels improves semi-supervised deep learning results

The recently proposed Mean Teacher has achieved state-of-the-art results...
research
03/06/2017

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

The recently proposed Temporal Ensembling has achieved state-of-the-art ...
research
10/07/2016

Temporal Ensembling for Semi-Supervised Learning

In this paper, we present a simple and efficient method for training dee...
research
09/03/2019

Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning

Recently, consistency-based methods have achieved state-of-the-art resul...
research
04/20/2020

Local Clustering with Mean Teacher for Semi-supervised Learning

The Mean Teacher (MT) model of Tarvainen and Valpola has shown favorable...
research
03/17/2020

Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions

For semi-supervised learning on graphs, we study how initial kernels in ...
research
03/15/2012

Online Semi-Supervised Learning on Quantized Graphs

In this paper, we tackle the problem of online semi-supervised learning ...

Please sign up or login with your details

Forgot password? Click here to reset