3
votes
Accepted
Topic classification on text data with no/few labels
A feasible approach would be to take a pre-trained model, like BERT, and fine-tune it on a small labeled dataset.
For that, you may use Huggingface's Transformers, which makes all the steps in the ...
- 27.5k
3
votes
How to approach semi-supervised binary classification problem with few labels only from one class?
I see two approaches:
either you do all your process using only the positive class, so based on one class classification approaches such as isolation forest, one class SVM, recontruction error of ...
- 1,435
3
votes
Accepted
What is the difference between all the different types of learning within machine learning?
Supervised Learning
In general, supervised learning refers to a situation in which you have some $X$ that is related to $y$, so that you can model how both are related (on average). In this case you ...
- 7,776
3
votes
Accepted
suggest ingredients based on recipe title
If the user inputs a title, then you could construct a system which finds the most similar titles in the corpus, and outputs the ingredients in the retrieved recipes. Some ideas below:
1) Represent ...
3
votes
Why positive-unlabeled learning?
A couple of points I have since found myself:
I was right in suspecting that self-training could be used for PU learning. In fact, I found the original paper on PU Learning, and indeed the paper is a ...
- 3,430
3
votes
General strategy for imbalanced, semi-supervised, sparse problem
It's a binary semi-supervised classification problem. First, establish a base-line for the supervised case. Then try if the unlabeled data helps
Supervised
From your labeled data: create a training, ...
- 19.2k
2
votes
Generic strategy for object detection
The framework you cope with is semi supervised. You have mostly unlabelled data and you can have some labeled data by manual labelling.
Active learning is one method to cope with the situation, by ...
- 2,663
2
votes
Why positive-unlabeled learning?
Why can they not just use a binary classifier where the negative
class=unlabeled?
E.g., when there are only a small portion of data are labeled as positive samples. It happens in reality where you ...
- 188
2
votes
General strategy for imbalanced, semi-supervised, sparse problem
Given your time budget and the potential challenges associated with class imbalance, I'd throw away the unlabelled data and use supervised learning on the labelled data. Try a simple classifier, e.g.,...
- 3,411
1
vote
Accepted
Why weak supervision works?
Weak supervision only works better than classic labeling in the case of weak data, but with a large volume.
Why? Because it considers several incomplete features and applies them to a general ...
- 4,904
1
vote
forcasting anomaly in products
Each of your observations is associated 120 features x 1000 measures matrix. I would start with something simple and reduce the matrix to be 1-dimensional to able to do standard ML. For example, you ...
- 944
1
vote
Accepted
Semi-supervised classification with SelfTrainingClassifier: no training after calling fit()
The reason you are not seeing any verbose output from the model fitting and no change in the model's labels is because the treshold you are currently using is too high, which doesn't allow the model ...
- 8,197
1
vote
Accepted
What the differences between self-supervised/semi-supervised in NLP?
Semi-supervised learning is having label for a fraction of data, but in self-supervised there is no label available. Imagine a huge question/answer dataset. No one labels that data but you can learn ...
- 6,712
1
vote
Accepted
Extract key phrases for binary outcome
There are a variety of techniques that you could use, depending on what you would like to do.
If your goal is to gain insight into the phrases that are being used in each group, then I'd recommend ...
- 231
1
vote
Accepted
Pros and Cons of Positive Unlabeled learning?
I don't think it's possible to know for sure if PU learning would work in your setting or not. It's certainly relevant to cases like the one you describe, so it would be worth trying. But there are ...
- 25.9k
1
vote
Identifying templates from SMS text
I'm not sure I understand your problem very well but let's see.
First let me try to formalize the task as a ML problem:
Identifying the SMS of interest is a binary classification task. Your "...
- 25.9k
1
vote
Supervised clustering
To be honest, I have never heard of "semi-supervised clustering" until right now. There are quite a few clustering techniques out there. Here are 7 popular tequines for clustering. I put together ...
- 613
1
vote
Supervised clustering
It's classification, isn't it?
You have labeled training data. You want to label your test set accordingly. Use a classifier...
- 8,114
1
vote
Supervised clustering
What you are looking for is called KNN algorithm, also knows as k-nearest neighbours. It’s a supervised algorithm where you have points and their clusters given and ...
- 841
1
vote
Accepted
Is there an algorithm for categorizing unlabeled samples into K classes?
Best solution would be to use the inception pertained model in your case as it's very good with over 1000 classes. Also you can label some of the data and make a CNN in Tensforflow, and then use this ...
- 56
1
vote
What is the convergence criteria of a semi-supervised learning algorithm?
Most of the semi-supervised methods are heuristics and more or less are modifications of the standard supervised learning algorithms, where you are trying to take into account unlabeled data ...
1
vote
Accuracy after selftraining didn't change
Well, that is a bit of a turn down but: your model has limitations.
If the 50.000 data forms a complete set for your problem that means that more data won't be needed or helpful.
What do I mean by ...
- 1,674
1
vote
Accepted
Adapting Neural Network to new domain without labels
I think those are one of the most cited papers:
https://arxiv.org/pdf/1409.7495.pdf
http://www.jmlr.org/papers/volume17/15-239/15-239.pdf
http://openaccess.thecvf.com/content_cvpr_2017/paper/...
- 1,686
1
vote
how to build a predictive model without training data neither historical data
If you do not have data then I think the problem is more of research than Machine Learning.
Ask your research team to gather primary data about the product by conducting surveys, polls,etc.
...
- 788
1
vote
Accepted
Semi Supervised Learning without label propagation
One strategy that seems good here is instance-level constrained clustering. These methods are semi-supervised algorithm that have "must-link" and "cannot-link" constraints between instances of known ...
- 947
1
vote
Time series binary classificaiton with labelling issues
From your description of the data, this is not a time-series problem. Time is not a factor here, for each user you have a set of variables after you choose a time threshold. Although you seek the "...
- 278
1
vote
Can You Purposely Bias A Clustering Model?
In constrained clustering you can provide examples of objects that should, or that must not, be in the same cluster.
This can be used, e.g., for model selection: run several times and return the ...
- 8,114
1
vote
Custom conditional loss function in Keras
You should be able to solve this with currying. Make a function that takes the label as input and returns a function which takes y_true and ...
- 652
1
vote
Why positive-unlabeled learning?
Taking the specific example of Collaborative-Filtering recommender systems, an initial dataset containing a large percentage of positive examples and a small percentage of unlabelled examples for one ...
- 11
1
vote
Why positive-unlabeled learning?
Whenever you have skewed data-set, it means that you know a typical class better than the others. In such cases it means that the data is your knowledge and is not in a way that finds the minimum of ...
- 14.2k
Only top scored, non community-wiki answers of a minimum length are eligible