اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدActive Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
137
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because a) standard assumptions for machine-learned model selection procedures break down and b) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting (IW), co-training (CT), and active learning (AL). We argue that AL---where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up---is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and OGLE, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply active learning to classify variable stars in the ASAS survey, finding dramatic improvement in our agreement with the ACVS catalog, from 65.5% to 79.5%, and a significant increase in the classifiers average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.
قيم البحث
اقرأ أيضاً
Modern computing and communication technologies can make data collection procedures very efficient. However, our ability to analyze large data sets and/or to extract information out from them is hard-pressed to keep up with our capacities for data co
llection. Among these huge data sets, some of them are not collected for any particular research purpose. For a classification problem, this means that the essential label information may not be readily obtainable, in the data set in hands, and an extra labeling procedure is required such that we can have enough label information to be used for constructing a classification model. When the size of a data set is huge, to label each subject in it will cost a lot in both capital and time. Thus, it is an important issue to decide which subjects should be labeled first in order to efficiently reduce the training cost/time. Active learning method is a promising outlet for this situation, because with the active learning ideas, we can select the unlabeled subjects sequentially without knowing their label information. In addition, there will be no confirmed information about the essential variables for constructing an efficient classification rule. Thus, how to merge a variable selection scheme with an active learning procedure is of interest. In this paper, we propose a procedure for building binary classification models when the complete label information is not available in the beginning of the training stage. We study an model-based active learning procedure with sequential variable selection schemes, and discuss the results of the proposed procedure from both theoretical and numerical aspects.
The accurate automated classification of variable stars into their respective sub-types is difficult. Machine learning based solutions often fall foul of the imbalanced learning problem, which causes poor generalisation performance in practice, espec
ially on rare variable star sub-types. In previous work, we attempted to overcome such deficiencies via the development of a hierarchical machine learning classifier. This algorithm-level approach to tackling imbalance, yielded promising results on Catalina Real-Time Survey (CRTS) data, outperforming the binary and multi-class classification schemes previously applied in this area. In this work, we attempt to further improve hierarchical classification performance by applying data-level approaches to directly augment the training data so that they better describe under-represented classes. We apply and report results for three data augmentation methods in particular: $textit{R}$andomly $textit{A}$ugmented $textit{S}$ampled $textit{L}$ight curves from magnitude $textit{E}$rror ($texttt{RASLE}$), augmenting light curves with Gaussian Process modelling ($texttt{GpFit}$) and the Synthetic Minority Over-sampling Technique ($texttt{SMOTE}$). When combining the algorithm-level (i.e. the hierarchical scheme) together with the data-level approach, we further improve variable star classification accuracy by 1-4$%$. We found that a higher classification rate is obtained when using $texttt{GpFit}$ in the hierarchical model. Further improvement of the metric scores requires a better standard set of correctly identified variable stars and, perhaps enhanced features are needed.
In modern astronomy, machine learning as an raising realm for data analysis, has proved to be efficient and effective to mine the big data from the newest telescopes. By using support vector machine (SVM), we construct a supervised machine learning a
lgorithm, to classify the objects in the Javalambre-Photometric Local Universe Survey (J-Plus). The sample is featured with 12-waveband, and magnitudes is labeled with spectrum-based catalogs, including Sloan Digital Sky Survey spectroscopic data, Large Sky Area Multi-Object Fiber Spectroscopic Telescope, and VERONCAT - Veron Catalog of Quasars & AGN. The performance of the classifier is presented with the applications of blind test validations based on RAdial Velocity Extension, Kepler Input Catalog, 2 MASS Redshift Survey, and UV-bright Quasar Survey. The accuracies of the classifier are 96.5% in blind test and 97.0% in training cross validation. The F_1-scores are 95.0% for STAR, 92.9% for GALAXY and 87.0% for QSO. In the classification for J-Plus catalog, we develop a new method to constrain the potential extrapolation.
We report a framework for spectroscopic follow-up design for optimizing supernova photometric classification. The strategy accounts for the unavoidable mismatch between spectroscopic and photometric samples, and can be used even in the beginning of a
new survey -- without any initial training set. The framework falls under the umbrella of active learning (AL), a class of algorithms that aims to minimize labelling costs by identifying a few, carefully chosen, objects which have high potential in improving the classifier predictions. As a proof of concept, we use the simulated data released after the Supernova Photometric Classification Challenge (SNPCC) and a random forest classifier. Our results show that, using only 12% the number of training objects in the SNPCC spectroscopic sample, this approach is able to double purity results. Moreover, in order to take into account multiple spectroscopic observations in the same night, we propose a semi-supervised batch-mode AL algorithm which selects a set of $N=5$ most informative objects at each night. In comparison with the initial state using the traditional approach, our method achieves 2.3 times higher purity and comparable figure of merit results after only 180 days of observation, or 800 queries (73% of the SNPCC spectroscopic sample size). Such results were obtained using the same amount of spectroscopic time necessary to observe the original SNPCC spectroscopic sample, showing that this type of strategy is feasible with current available spectroscopic resources. The code used in this work is available in the COINtoolbox: https://github.com/COINtoolbox/ActSNClass .
Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a models generalizability, especially when typical co-occurrence patterns are absent. This wor
k focuses on addressing such contextual biases to improve the robustness of the learnt feature representations. Our goal is to accurately recognize a category in the absence of its context, without compromising on performance when it co-occurs with context. Our key idea is to decorrelate feature representations of a category from its co-occurring context. We achieve this by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature subspace that represents both categories and context. Our very simple yet effective method is extensible to two multi-label tasks -- object and attribute classification. On 4 challenging datasets, we demonstrate the effectiveness of our method in reducing contextual bias.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
