Multi-label Classification: a survey

Tidake, Vaishali S.; Sane, S. S.

doi:10.14419/ijet.v7i4.19.28284

Cited by 17 publications

(17 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance was evaluated based on eight examplebased measures, namely hamming loss, ranking loss, coverage, one error, average precision, accuracy, F1, subset accuracy, and two label-based measures, namely macro and micro F1 (Tsoumakas et al 2009) (zhang et al 2014) (Tidake et al 2018). For the first four measures, a smaller value is expected, denoted by (↓), whereas for the remaining, a higher value is desired, denoted by (↑).…”

Section: Resultsmentioning

confidence: 99%

“…Transformation and adaptation are two approaches used by many researchers for designing multi-label algorithms. The ensemble of the existing methods is the third approach for the same (Tsoumakas et al 2009) (zhang et al 2014) (Tidake et al 2018). Br (Wever et al, 2020), MLknn (zhang et al 2007), andrAkEL (Tsoumakas et al 2009) follow these approaches, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Multi-label Classification using Attribute and Instance Selection

Sane¹

2020

Biosci. Biotech. Res. Comm

View full text Add to dashboard Cite

Both attribute and instance selection is proven to be beneficial to reduce the computational complexity of classifiers while improving their accuracy. Instances in multi-label data are associated with multiple labels. Hence the process of attribute selection from multi-label data is different as compared to single-label classification. Either transformation or adaptation approaches are used by various researchers while performing attribute selection. In this paper, attribute selection and sampling are performed on the multi-label data. This pre-processed multi-label data is then fed to the proposed algorithms, namely MLFLD and its extension MLFLD-MAXP. An empirical evaluation is carried out to study the behaviour of proposed multi-label classifiers. The methods used in this work are defined as algorithms MLFS, MLIS, and MLFSIS. Comparing proposed algorithms with and without MLFS, MLIS, and MLFSIS has shown the effectiveness of using only sampling, or attribute selection followed by sampling on multi-label data. Attribute and instance selection together are noticed to be very useful for the performance enhancement of proposed algorithms over only attribute or instance selection.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Multi-label Classification using Attribute and Instance Selection

Sane¹

2020

Biosci. Biotech. Res. Comm

View full text Add to dashboard Cite

show abstract

“…MLC has many applications in various domains including text classification [22,23], image classification [24], bioinformatics [25], genre classification [26], and social media analysis [27]. More details could be found in references [28,29]. Moreover, MLC has leveraged its power in RSs world too.…”

Section: Multilabel Classification and Related Workmentioning

confidence: 99%

Developing Tourism Users’ Profiles with Data-Driven Explicit Information

Norouzi

Baziyad

Noghabi

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In recommender systems (RSs), explicit information is often preferred over implicit because it is much more accurate than implicit or predicted information; for example, the user can enter information about his interests directly into the system, and the system will generate accurate recommendations for him. Receiving explicit information, however, may be difficult for a system. Explicit demographic information might be uncomfortable for some users, and extremely common questions, such as race, gender, income, and age, can lead to bias and unfair recommendations. As a result, in this study, we propose a method, in which information collected from a new user does not contain demographic information, and enquired explicit information is data driven. Users’ interest in tourism activities is used to identify seven categories of tourism. The mapping between extracted categories and activities is established with a multilabel classification (MLC) algorithm. The user’s interest in 18 tourism activities is predicted by rating only seven tourism categories. Common MLC algorithms with different classifiers were used to evaluate the proposed method. The best result relates to binary relevance with the Naïve Bayes classifier, which also outperforms the entitled algorithms in collaborative filtering (CF) systems as baseline models. The proposed method can capture users’ interests and develop their profiles without receiving demographic information. Also, compared to CF, in addition to a slight advantage in metrics, it only requires seven ratings to predict user interest in 18 activities. In contrast, CF algorithms require at least 15 user ng records to predict user interest in unknown activities (3-4 activities) to achieve a performance close to the proposed method.

show abstract

“…In transformationbased methods, multi-label data is converted to new single label data to apply regular single-label classification. On the other hand, in the adaptation-based category, this is attempted to modify the basic single-label algorithm to handle multi-label data [21].…”

Section: Introductionmentioning

confidence: 99%

Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images

Kalra¹,

Adnan²,

Hemati³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning methods such as convolutional neural networks (CNNs) are difficult to directly utilize to analyze whole slide images (WSIs) due to the large image dimensions. We overcome this limitation by proposing a novel two-stage approach. First, we extract a set of representative patches (called mosaic) from a WSI. Each patch of a mosaic is encoded to a feature vector using a deep network. The feature extractor model is fine-tuned using hierarchical target labels of WSIs, i.e., anatomic site and primary diagnosis. In the second stage, a set of encoded patch-level features from a WSI is used to compute the primary diagnosis probability through the proposed Pay Attention with Focus scheme, an attention-weighted averaging of predicted probabilities for all patches of a mosaic modulated by a trainable focal factor. Experimental results show that the proposed model can be robust, and effective for the classification of WSIs.

show abstract

Multi-label Classification: a survey

Cited by 17 publications

References 49 publications

Efficient Multi-label Classification using Attribute and Instance Selection

Efficient Multi-label Classification using Attribute and Instance Selection

Developing Tourism Users’ Profiles with Data-Driven Explicit Information

Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images

Contact Info

Product

Resources

About