A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Collaboration Based Multi-Label Learning
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
It is well-known that exploiting label correlations is crucially important to multi-label learning. ...
Based on this assumption, we first propose a novel method to learn the label correlations via sparse reconstruction in the label space. ...
Based on this assumption, a novel multi-label learning approach named CAMEL, i.e., CollAboration based Multi-labEl Learning, is proposed. ...
doi:10.1609/aaai.v33i01.33013550
fatcat:bjad4i457bepva2hco53ovihte
Collaboration based Multi-Label Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It is well-known that exploiting label correlations is crucially important to multi-label learning. ...
Based on this assumption, we first propose a novel method to learn the label correlations via sparse reconstruction in the label space. ...
Based on this assumption, a novel multi-label learning approach named CAMEL, i.e., CollAboration based Multi-labEl Learning, is proposed. ...
arXiv:1902.03047v1
fatcat:kltrocwjrzh37bb27ztuwos4uy
Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Multi-view Multi-instance Multi-label Learning(M3L) deals with complex objects encompassing diverse instances, represented with different feature views, and annotated with multiple labels. ...
In this paper, we propose a collaborative matrix factorization based solution called M3Lcmf. ...
Conclusion In this paper, we proposed a collaborative matrix factorization based multi-view multi-instance multi-label learning approach called M3Lcmf. ...
arXiv:1905.05061v2
fatcat:rhkqgigc3rbrpgzf2iaetdlepq
Multi-View Multi-Instance Multi-Label Learning Based on Collaborative Matrix Factorization
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Multi-view Multi-instance Multi-label Learning (M3L) deals with complex objects encompassing diverse instances, represented with different feature views, and annotated with multiple labels. ...
.\ In this paper, we propose a collaborative matrix factorization based solution called M3Lcmf. ...
This investigation justifies our motivation
Conclusion In this paper, we proposed a collaborative matrix factorization based multi-view multi-instance multi-label learning approach called M3Lcmf. ...
doi:10.1609/aaai.v33i01.33015508
fatcat:jszbhnadbrbmtckzdj3hd26ucy
Comprehensive study and Analysis of Extreme Multi-Label Classification Approach
2020
International Journal of Advanced Trends in Computer Science and Engineering
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper discussed different approaches for large scale Recommendation System using Extreme Multi-Label Classification Approach and empirical evaluation carried out on three multi-label datasets which ...
In Recommendation System, the main goal is to recommend users based on the available data. ...
XML-CNN [11] is the deep learning based CNN (Convolutional Neural Network) for extreme multi-label data. ...
doi:10.30534/ijatcse/2020/83922020
fatcat:qzgi7mtk4bfnbk4dmdjblp373y
Semi-Supervised learning with Collaborative Bagged Multi-label K-Nearest-Neighbors
2019
Open Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, a Collaborative Bagged Multi-label K-Nearest-Neighbors (CobMLKNN) algorithm is proposed, that extend the co-Training paradigm by a Multi-label K-Nearest-Neighbors algorithm. ...
The manual annotation of available datasets is time-consuming and need a huge effort from the expert, especially for Multi-label applications in which each example of learning is associated with many labels ...
Conclusion In this work, we studied the problem of semi-supervised learning for a Multi-label framework. We proposed collaborative Multi-label learning using an ensemble learning named CobMLKNN. ...
doi:10.1515/comp-2019-0017
fatcat:24kgnww2mnattcnbjl25f5osda
Collaborative Multi-agent Learning for MR Knee Articular Cartilage Segmentation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The key contribution is the adversarial learning based collaborative multi-agent segmentation network. ...
The collaborative learning is driven by an adversarial sub-network. ...
(c) demonstrates the cartilage labels in 3D.
Fig. 2 . 2 Flowchart of the collaborative multi-agent learning for cartilage segmentation. ...
arXiv:1908.04469v1
fatcat:gwlpezkk3vfehkwbzuzzbwnlsm
Stylometric Authorship Attribution of Collaborative Documents
[chapter]
2017
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Based on the results of these experiments and knowledge of the multi-label classifiers used, we propose a hypothesis to explain this overall poor performance. ...
Additionally, we perform authorship attribution of pre-segmented text from the Wikia dataset, and show that while this performs better than multi-label learning it requires large amounts of data to be ...
Background and Related Work
Multi-Label Learning There have been a number of proposed techniques for multi-label learning that we consider in this work. ...
doi:10.1007/978-3-319-60080-2_9
fatcat:usmbstcxsna3zadtwwfrmbkltq
CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
CollaborER consists of two phases, i.e., automatic label generation (ALG) and collaborative ER training (CERT). ...
In this paper, we present CollaborER, a self-supervised entity resolution framework via multi-features collaboration. ...
CERT is composed of two phases, i.e., (i) multi-relational graph feature learning (MRGFL) and (ii) collaborative sentence feature learning (CSFL). ...
arXiv:2108.08090v2
fatcat:xcwnwpodanh5tjgwcgxikjkdfq
Activity-edge centric multi-label classification for mining heterogeneous information networks
2014
Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '14
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Second, we utilize the label vicinity to capture the pairwise vertex closeness based on the labeling on the activity-based collaboration multigraph. ...
Multi-label classification of heterogeneous information networks has received renewed attention in social network analysis. ...
This material is based upon work partially supported by the NSF under Grants IIS-0905493, CNS-1115375, IIP-1230740, and a grant from Intel ISTC on Cloud Computing. ...
doi:10.1145/2623330.2623737
dblp:conf/kdd/ZhouL14
fatcat:nkfhap7gtbgmhkyjum3gsfzpii
Semi-supervised Multi-label Learning by Solving a Sylvester Equation
[chapter]
2008
Proceedings of the 2008 SIAM International Conference on Data Mining
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Multi-label learning refers to the problems where an instance can be assigned to more than one category. ...
In this paper, we present a novel Semi-supervised algorithm for Multi-label learning by solving a Sylvester Equation (SMSE). ...
This encourages us to propose the following graph-based semi-supervised algorithm for multi-label learning, i.e. ...
doi:10.1137/1.9781611972788.37
dblp:conf/sdm/ChenSWZ08
fatcat:rwimejcpzjbgdhj4rducybsehu
A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To address this problem, we propose a Consensual Collaborative Multi-Label Learning (CCML) method. ...
The group lasso module detects the potentially noisy labels by estimating the label uncertainty based on the aggregation of two collaborative networks. ...
CONCLUSION In this paper, a novel Consensual Collaborative Multi-label Learning (CCML) method has been presented. ...
arXiv:2105.05496v2
fatcat:f4cwlafib5durlna62i27mezyq
Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a novel multi-source domain adaptation framework based on collaborative learning for semantic segmentation. ...
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. ...
Conclusion In this paper, we present an effective multi-source domain adaptation framework for semantic segmentation based on collaborative learning. ...
arXiv:2103.04717v3
fatcat:7jidp4uyjrattbfpdj4nu4ehqy
An Attention-based Collaboration Framework for Multi-View Network Representation Learning
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. ...
Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. ...
To the best of our knowledge, this is the rst e ort to adopt the a ention-based approach in the problem of multi-view network representation learning. ...
arXiv:1709.06636v1
fatcat:uk5memuwrbe5jfa5jh5c2imwlu
Multi-Label Noise Robust Collaborative Learning Method for Remote Sensing Image Classification
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To address this problem, we propose a novel multi-label noise robust collaborative learning (RCML) method to alleviate the negative effects of multi-label noise during the training phase of a CNN model ...
However, multi-label noise (which can be associated with wrong and missing label annotations) can distort the learning process of the MLC methods. ...
the European Research Council (ERC) through the ERC-2017-STG BigEarth Project under Grant 759764 and by the German Ministry for Education and Research as BIFOLD -Berlin Institute for the Foundations of Learning ...
arXiv:2012.10715v5
fatcat:26g4qfytafh67huj4lrnzrqfeq
« Previous
Showing results 1 — 15 out of 152,565 results