Questions tagged [semi-supervised-learning]

For questions related to the machine learning technique called semi-supervised learning, which is a combination of supervised and unsupervised learning.

9 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
1answer
159 views

How to deal with a small amount of labeled samples?

I'm trying to develop skills to deal with very small amounts of labeled samples (250 labeled/20000 total, 200 features) by practicing on Kaggle "Don't Overfit" dataset (Traget_Practice have ...
1
vote
0answers
15 views

Why is it difficult to propagate intransitive relations over a graph?

In the paper Semi-Supervised Learning by Mixed Label Propagation, they say One major limitation with most graph-based approaches is that they are unable to explore dissimilarity or negative ...
1
vote
0answers
19 views

Model output segmentation maps which are not full

I created a VGG based U-Net in order to perform image segmentation task on yeast cells images obtained by a microscope. There are a couple of problems with the data: There is inhomogeneity in the ...
0
votes
0answers
2 views

Why is/can node classification (graph machine learning) be semi-supervised while graph classification is supervised?

I was reading about different graph machine learning tasks in this book (Chapter 1) here and to learn about node classification and graph classification tasks. Then I looked at this paper here, which ...
0
votes
0answers
20 views

Validation set performance increasing even after seemingly overfit on training set

I am training a semi-supervised GAN network using data from multiple subjects. I separated the labeled and unlabeled data based on my subjects, so there is no leakage, while having much more unlabeled ...
0
votes
0answers
12 views

How exactly is masking performed in the training part of the paper "Semi-Supervised Classification with Graph Convolutional Networks"?

I am struggling to understand the training part of the paper Semi-Supervised Classification with Graph Convolutional Networks (2017) by Thomas Kipf and Max Welling. The GitHub repo is here. I do not ...
0
votes
0answers
13 views

How can I classify text documents arriving as a stream

To create a classifier for a fixed corpus of texts is straightforward. Take all the documents, form the tfidf matrix and from that matrix take a subset that is tagged accordingly. The classifier built ...
0
votes
0answers
43 views

How can the expectation-maximization improve the classification?

I am learning the expectation-maximization algorithm from the article Semi-Supervised Text Classification Using EM. The algorithm is very interesting. However, the algorithm looks like doing a ...
0
votes
0answers
34 views

Semi-supervised: Can I predict the label of purposely unlabelled observations?

Let's say I have a data set with of length N. A small proportion N2 is labeled. Can I remove some labels and then 'reverse' this action with a trained neural network? I could then use the same process ...