Questions tagged [domain-adaptation]
The domain-adaptation tag has no usage guidance.
38
questions
0
votes
0
answers
27
views
Which meta-learning algorithms are well-suited for "many-shot learning" scenarios, where the target training set is large?
Much of the meta-learning literature deals with the few-shot learning problem of using data from a diverse set of "source" tasks (the meta-dataset) in order to train a model that can quickly ...
- 101
1
vote
0
answers
68
views
Why does the best performing adapter-based parameter-efficient fine-tuning depend on the language model being fine-tuned?
https://arxiv.org/abs/2304.01933 shows that the best performing adapter-based parameter-efficient fine-tuning depends on the language model being fine-tuned:
E.g., LORA is the best adapter for LlaMa-...
- 45.9k
0
votes
0
answers
41
views
Generalization bounds with active learning in linear and kernel regression
I have been reading a bit of machine learning theory as a hobby. I do not have all the vocabulary that is used in the ML theory literature so please bear with me. I have found active learning really ...
- 1
1
vote
0
answers
31
views
Same architecture but training in two different domains: what is it called?
I am trying to find the keyword (if there is any) for the technique in which we use the same deep learning architecture that works well in one domain and train it again in another domain to find out ...
- 115
1
vote
0
answers
35
views
Training with unlabeled data and the probability of correct classification
Suppose we have two binary classifiers based on deep learning. The second classifier is able to tell me with a probability not very high but better than a random guess (let's say 70%), if the ...
- 121
2
votes
1
answer
321
views
For "fine-tuning", does the "domain adaptation" approach make sense?
I understand "domain adaptation" to be a type of "transfer-learning" technique.
Domain Adaptation:
By applying knowledge obtained from a domain with sufficient teacher labels (...
- 21
1
vote
1
answer
1k
views
The difference between transfer learning, fine-tuning, and domain adaptation
I was wondering if someone could clearly explain the extent of transfer learning, fine-tuning, and domain adaptation. From my understanding, both fine-tuning and domain adaptation are subcategories of ...
- 13
2
votes
1
answer
38
views
Transfer learning: As simple as running trained models on new data?
So there's a domain of interest where the machine learning models are all specific to one entity. Let's call it a building. So there's a model made for every building. The literature in the domain all ...
- 313
1
vote
0
answers
42
views
reproducing kernel hilbert space notation
I'm trying to understand reproducing kernel Hilbert spaces (RKHSs) from scientific papers, however I don't find any gentle introduction. However, my main problem, at the moment, seems to be to ...
- 747
0
votes
1
answer
2k
views
Domain Generalization vs Domain Adaptation
What is the difference between domain generalization and domain adaptation?
According to this paper, domain adaptation deals with unlabelled target domain whereas domain generalization can't do it. ...
- 329
0
votes
1
answer
527
views
How to check whether two image datasets come from the same distribution?
In the literature of transfer learning and domain adaptation everyone talks about two datasets having different feature spaces and different distributions. In case of having image datasets, I think I ...
- 177
3
votes
0
answers
273
views
Random Forest vs Gradient Boosting out of distribution
I'm working on a classification task where I have data from a certain company for years between 2017 and 2020. Trying to train different models (Random Forest, XgBoost, LightGBM, Catboost, Explainable ...
3
votes
1
answer
125
views
Domain adaptation under covariate shift: estimating density ratio through a classifier
In domain adaptation under covariate shift, one approach is to weight the instances from the source domain by a factor $\frac{p_T(x)}{p_S(x)}$ in the training, where $p_S(x)$ and $p_T(x)$ represent ...
- 926
0
votes
1
answer
540
views
Meta/ Few-shot Learning for time series regression
I am working on the calibration of low-cost air sensor data (a time series regression problem). My primary focus is to use some meta/ few-shot learning approach to solve this problem with a lesser ...
1
vote
1
answer
658
views
Why GAN use adversarial MinMax formulation rather than Min formulation?
For generative adversarial neural network, originally Goodfellow used a MinMax formulation as $\text{Min}_D\text{Max}_G \mathbb{E}_{real}logD(x) dx+ \mathbb{E}_{fake}(1-D(G(z)))dz$. As long as the ...
- 115
1
vote
0
answers
72
views
Loss values in a Domain Adversarial
I have been using ResNet-50 with Domain-Adversarial network. I observed an oscillation in the loss values from the evaluation as you can see in the figures, this oscillation was not observed when ...
- 11
0
votes
0
answers
65
views
Generalisation accuracy in Domain Adaptation
Usually, in all the Unsupervised Domain Adaptation literature the test accuracy (on the target domain obviously) is calculated on the unlabelled target examples that the model has already seen during ...
- 1
0
votes
1
answer
65
views
Neural networks for domain/style transformation?
Is there a neural network that can take data from one distribution and transform it so that it looks as if it were from another distribution, given those two distributions are closely related in some ...
- 85
3
votes
1
answer
299
views
Multiple-domain adaptation vs multi-task learning
I am confused with the definitions of domain adaptation and multi-task learning.
I have K datasets, each with the same feature and label space and thus the same learning problem, but with different ...
- 31
2
votes
1
answer
66
views
Looseness of the definition of domain adaption
I am a bit intrigued about “domain shift” concept. Specifically, in part 5 of the paper “Coupled Generative Adversarial Networks”, it reads
We studied the problem of adapting a digit classifier ...
- 223
9
votes
4
answers
4k
views
Why is Permuted MNIST good for evaluating continual learning models?
While I was reading papers about continual learning, I found that many researchers use permutated MNIST to evaluate their approach.
I understand what it is but it ...
- 135
2
votes
0
answers
383
views
Using PCA in domain adaptation
In literature, I see people using (Kernelized) Principle Component Analysis, not for feature extraction, but for domain adaptation. In other words, I have data from a source domain and I would like to ...
- 21
2
votes
0
answers
74
views
How to integrate expert knowledge to outlier detection algorithms?
Suppose I have a dataset of 20 features, X1, X2..X20.
...
- 947
1
vote
1
answer
78
views
ML methods for cold start - domain adaptation
Imagine a scenario: You work with credit card transactions and you use ML to assign probabilities to each transaction to be fraudulent or not. You operate in different countries and you have ML models ...
- 111
1
vote
1
answer
196
views
Testing the scope of application of a logistic regression model
My aim is to assess whether I can apply a logistic regression that was fitted on a sample A (where I have explanatory variables and the outcomes) to a different sample B where I don't know the ...
- 3,396
1
vote
1
answer
45
views
Robust machine learning for slightly different class proportions in multiple data sets
Say we have n similar data sets, with the same variables, and outcome labels x and y. In these data sets, domains slightly differ as suggested by the proportion of the minority class x (ranging from 1%...
- 219
0
votes
0
answers
82
views
Domain knowledge or data dredging?
I have a binary classification problem where I'm required to classify transactions as anomalous or normal (1 or 0 respectively), with anomalies being the rarer instance.
With what I know to be true ...
- 1
4
votes
2
answers
2k
views
Learn a mapping between two datasets using Neural Network
I have two matrices $A_1$ of size $N\times K$ and $A_2$ of size $M\times K$ which contain data and every row has a corresponding label $y \in {1, 2, 3}$. I want to learn a mapping between those two ...
- 61
1
vote
1
answer
163
views
Ratio of training/testing data different to real life?
My company wants to build a model that will be used to predictive conversion that is usually about 2%.
However every sample we purchase (converted or unconverted) is expensive. So my question is:
How ...
- 47
42
votes
4
answers
71k
views
Maximum Mean Discrepancy (distance distribution)
I have two data sets (source and target data) which follow different distributions. I am using MMD - that is a non-parametric distribution distance - to compute marginal distribution between the ...
- 521
6
votes
3
answers
4k
views
regression with constraints
I have some domain knowledge I want to use in a regression problem.
Problem statement
The dependent variable $y$ is continuous.
The independent variables are $x_1$ and $x_2$.
Variable $x_1$ is ...
- 1,533
37
votes
6
answers
32k
views
What is difference between 'transfer learning' and 'domain adaptation'?
Is there any difference between 'transfer learning' and 'domain adaptation'?
I don't know about context, but my understanding is that we have some dataset 1 and train on it, after which we have ...
- 2,187
0
votes
1
answer
1k
views
Can an unstandarized Beta distribution have a negative domain? [duplicate]
(*Question edited for clarification)
Does the lower bound of the unstandarized beta distribution always have to be bigger than 0?
- 1
1
vote
0
answers
35
views
What description fits this this learning scenario, is this a form of active learning?
A system is involved in dialog with a human partner.
The system has a model of a problem domain and knows mappings between words an concepts. The human has its own model of the problem domain and ...
- 111
4
votes
0
answers
81
views
What are some adaptive machine learning techniques that cater for data that may change slightly but is still correct? [closed]
Are there suitable machine learning techniques that may be applied to a continual stream of data and update its models for data that it believes to be different to the most representative case but ...
- 295
3
votes
2
answers
101
views
Biased classification because of data from different sites?
Working in neuroscience, we often classify data from different sites. Usually I balance my data for sites - if I have for instance to classify the data for some illness vs. normal health condition, ...
- 1,481
4
votes
1
answer
1k
views
Frustratingly Easy Domain Adaptation
I refer to the paper by called Frustratingly Easy Domain Adaptation (http://www.umiacs.umd.edu/~hal/docs/daume07easyadapt.pdf) where the feature space of both the source and target data are augmented ...
- 121
6
votes
1
answer
898
views
What are the most popular domain adaptation methods (for transfer learning)?
I understand supervised and unsupervised learning well, and would be able to identify some 'basic' examples of, for example, supervised classifcation as:
SVMs
Random Forests
Logistic Regression
...
- 255