Filters








394,539 Hits in 2.8 sec

Bi-directional Representation Learning for Multi-label Classification [chapter]

Xin Li, Yuhong Guo
2014 Lecture Notes in Computer Science  
Our experiments conducted on a variety of multilabel data sets demonstrate the efficacy of the proposed bi-directional representation learning model for multi-label classification.  ...  Multi-label classification is a central problem in many application domains.  ...  We compared the proposed bi-directional multi-label learning method with the following multi-label learning methods: -Binary relevance (BR).  ... 
doi:10.1007/978-3-662-44851-9_14 fatcat:q4dq2dkgdfdmjil2s2gwbbbqsm

Fast Direct Search in an Optimally Compressed Continuous Target Space for Efficient Multi-Label Active Learning

Weishi Shi, Qi Yu
2019 International Conference on Machine Learning  
Active learning for multi-label classification poses fundamental challenges given the complex label correlations and a potentially large and sparse label space.  ...  Experimental results over multiple realworld datasets and comparison with competitive multi-label active learning models demonstrate the effectiveness of the proposed framework.  ...  Extensive experiments conducted on real-world multi-label data demonstrate the effectiveness of the proposed framework. We identify two interesting future directions.  ... 
dblp:conf/icml/Shi019 fatcat:ae5gqdqxyjfq5pnaqfd4lxwgl4

Bi-directional LSTM-CNNs-CRF for Italian Sequence Labeling and Multi-Task Learning

Pierpaolo Basile, Pierluigi Cassotti, Lucia Siciliani, Giovanni Semeraro
2017 Italian Journal of Computational Linguistics  
We exploit the same approach for the Italian language and extend it for performing a multi-task learning involving PoS-tagging and sentiment analysis.  ...  This architecture provided state of the art performance in several sequence labeling tasks for the English language.  ...  Multi-task learning We extend the previous architecture for performing multi-task learning. In particular, we want to jointly learn PoS-tag, polarity and irony.  ... 
doi:10.4000/ijcol.553 fatcat:ujosz5ovwjcbddcz47e47wrrje

Direct Multi-label Linear Discriminant Analysis [chapter]

Maria Oikonomou, Anastasios Tefas
2013 Communications in Computer and Information Science  
In this paper, the Direct Multi-label Linear Discriminant Analysis method is proposed for dimensionality reduction of multilabel data.  ...  Similar to single label problems, multi label problems also suffer from high dimensionality as multi label data often happens to have large number of features.  ...  Multi-label perceptron based algorithms have also been extended for multi-label learning.  ... 
doi:10.1007/978-3-642-41013-0_43 fatcat:ow5kegmjzzeitbmcar4tbun2fy

Transductive Multi-label Zero-shot Learning [article]

Yanwei Fu, Yongxin Yang, Tim Hospedales, Tao Xiang, Shaogang Gong
2015 arXiv   pre-print
In this paper, for the first time, we investigate and formalise a general framework for multi-label zero-shot learning, addressing the unique challenge therein: how to exploit multi-label correlation at  ...  Our zero-shot learning experiments on a number of standard multi-label datasets demonstrate that our method outperforms a variety of baselines.  ...  Hence we propose two more principled multi-label zero-shot algorithms -Direct Multi-label zero-shot Prediction (DMP) and Transductive Multi-label zero-shot Prediction(TraMP).  ... 
arXiv:1503.07790v1 fatcat:btznqtfc45bo5n6qsj5qhqjiee

Empirical Studies on Multi-label Classification

Tao Li, Chengliang Zhang, Shenghuo Zhu
2006 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06)  
In this paper, we present a comparative study on various multi-label approaches using both gene and scene data sets.  ...  In other words, these applications are multi-labeled, classes are overlapped by definition and each instance may be associated to multiple classes.  ...  Common approaches for multi-label problems include binary approach, Bayesian approach, and direct multiclass approach.  ... 
doi:10.1109/ictai.2006.55 dblp:conf/ictai/LiZZ06 fatcat:ps7pggc4m5gy5lle67ptrvv2ey

A survey of multi-view machine learning

Shiliang Sun
2013 Neural computing & applications (Print)  
Multi-view learning or learning with multiple distinct feature sets is a rapidly growing direction in machine learning with well theoretical underpinnings and great practical success.  ...  This paper reviews theories developed to understand the properties and behaviors of multi-view learning, and gives a taxonomy of approaches according to the machine learning mechanisms involved and the  ...  Multi-view supervised learning is almost direct to adapt if one already has a multi-view semi-supervised learning method. But we should note that these two problems are intrinsically distinct.  ... 
doi:10.1007/s00521-013-1362-6 fatcat:kzt7hibfo5axheedlaofw3pb7m

One Size Fits Many: Column Bundle for Multi-X Learning [article]

Trang Pham, Truyen Tran, Svetha Venkatesh
2017 arXiv   pre-print
Much recent machine learning research has been directed towards leveraging shared statistics among labels, instances and data views, commonly referred to as multi-label, multi-instance and multi-view learning  ...  We evaluate CLB on different types of data: (a) multi-label, (b) multi-view, (c) multi-view/multi-label and (d) multi-instance.  ...  Acknowledgement This work is partially supported by the Telstra-Deakin Centre of Excellence in Big Data and Machine Learning  ... 
arXiv:1702.07021v2 fatcat:x2h5ei5ezjabhb6ckucw6p2n7e

Multi-Label Transfer Learning for Multi-Relational Semantic Similarity [article]

Li Zhang, Steven R. Wilson, Rada Mihalcea
2019 arXiv   pre-print
This multi-label regression approach jointly learns the information provided by the multiple relations, rather than treating them as separate tasks.  ...  We propose a multi-label transfer learning approach based on LSTM to make predictions for several relations simultaneously and aggregate the losses to update the parameters.  ...  Comparison with Multi-Task Learning Neither multi-task nor multi-label learning have been used for multi-relational semantic similarity datasets.  ... 
arXiv:1805.12501v2 fatcat:3um7lbyqfzcevnaaivp4txjb3e

Multi-Label Transfer Learning for Multi-Relational Semantic Similarity

Li Zhang, Steven Wilson, Rada Mihalcea
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*  
This multi-label regression approach jointly learns the information provided by the multiple relations, rather than treating them as separate tasks.  ...  We propose a multi-label transfer learning approach based on LSTM to make predictions for several relations simultaneously and aggregate the losses to update the parameters.  ...  Comparison with Multi-Task Learning Neither multi-task nor multi-label learning have been used for multi-relational semantic similarity datasets.  ... 
doi:10.18653/v1/s19-1005 dblp:conf/starsem/ZhangWM19 fatcat:ozugcxpmmrft3hhfjsntsoqy74

Transductive Multi-class and Multi-label Zero-shot Learning [article]

Yanwei Fu, Yongxin Yang, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2015 arXiv   pre-print
In this paper we discuss two related lines of work improving the conventional approach: exploiting transductive learning ZSL, and generalising ZSL to the multi-label case.  ...  Recently, zero-shot learning (ZSL) has received increasing interest.  ...  With this synthetic dataset, we are able to propose two new multi-label algorithms -direct multi-label zero-shot prediction (DMP) and transductive multi-label zero-shot prediction (TraMP).  ... 
arXiv:1503.07884v1 fatcat:or4zahtjj5atpoxks5n4dilega

Learning Multiple Dense Prediction Tasks from Partially Annotated Data [article]

Wei-Hong Li, Xialei Liu, Hakan Bilen
2022 arXiv   pre-print
Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets.  ...  ), which we call multi-task partially-supervised learning.  ...  To evaluate the multi-task partially supervised learning, we consider one-label and random-label settings.  ... 
arXiv:2111.14893v3 fatcat:5ij72ybxyzf7jnwn6fhatpb4za

Learning safe multi-label prediction for weakly labeled data

Tong Wei, Lan-Zhe Guo, Yu-Feng Li, Wei Gao
2017 Machine Learning  
Extensive experiments on three weakly labeled learning tasks, namely, (i) semi-supervised multi-label learning; (ii) weak label learning and (iii) extended weak label learning, clearly show that our proposal  ...  It is desirable to learn safe multi-label prediction that will not hurt performance when weakly labeled data is involved in the learning procedure.  ...  Specifically, given Y 0 be the predictive label matrix based on direct supervised multi-label learning algorithms, e.g., binary relevance (Read et al. 2011) , we would like to learn a safe multi-label  ... 
doi:10.1007/s10994-017-5675-z fatcat:4cnd47b6wrcqhga2wykqsesgjm

Discovering and Exploiting Deterministic Label Relationships in Multi-Label Learning

Christina Papagiannopoulou, Grigorios Tsoumakas, Ioannis Tsamardinos
2015 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15  
In multi-label learning, each instance can be related with one or more binary target variables.  ...  The main motivation of multi-label learning algorithms is the exploitation of label dependencies in order to improve prediction accuracy.  ...  In several multi-label learning problems, the labels are organized as a tree or a directed acyclic graph, and there exist approaches that exploit such structure [2] .  ... 
doi:10.1145/2783258.2783302 dblp:conf/kdd/Papagiannopoulou15 fatcat:cezqk3xxxzfs7gpexxbqaavque

A Novel Multi-Feature Joint Learning Ensemble Framework for Multi-Label Facial Expression Recognition

Wanzhao Li, Mingyuan Luo, Peng Zhang, Wei Huang
2021 IEEE Access  
INDEX TERMS Multi-label, facial expression recognition, ResNet-18, deep learning.  ...  Some researchers have realized that facial expression recognition can be treated as a multi-label task, but they are still troubled by the inaccurate recognition of multi-label expressions.  ...  So, it is a novel and valuable direction which improves the method of deep learning in the area of multi-label facial expression recognition.  ... 
doi:10.1109/access.2021.3108838 fatcat:3zte75g56rf3zhhps4ffdlytp4
« Previous Showing results 1 — 15 out of 394,539 results