Ieee Transactions on Knowledge and Data Engineering 1 Multi-label Neural Networks with Applications to Functional Genomics and Text Categorization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

DOC: Deep Open Classification of Text Documents (2017, background): “(3) Note that although multi-label classification (Huang et al., 2013; Zhang and Zhou, 2006; Tsoumakas and Katakis, 2006) may also leverage multiple sigmoid functions, Eq.”
Mining Multi-label Data (2010, background): “BP-MLL [38] is an adaptation of the popular back-propagation algorithm for multilabel learning.”
Multi-target regression via input space expansion: treating targets as inputs (2012, background): “For example, the core idea in [37] was the optimization of a ranking loss function that takes into account label pairs, instead of the typical logistic loss of neural networks that looks at individual labels.”
Multi-instance multi-label learning (2008, methodology): “Here the mapping φ can be implemented with constructive clustering which was proposed by Zhou and Zhang [93] in transforming multi-instance bags into traditional single-instances.”
Multi-label Adversarial Perturbations (2018, methodology): “By adopting hinge loss similar to ML-CW, an alternative loss can be formulated as: The exponential function is chosen to severely penalize the ranking errors inspired by [14].”
A Literature Survey on Algorithms for Multi-label Learning (2010, background): “In BP-MLL [65], the error function for the very common neural network learning algorithm, back-propagation has been modified to account for multi-label data.”
Probabilistic Label Tree for Streaming Multi-Label Learning (2021, unknown): “• Deep-ML [35] introduces a shallow neural network as the multi-label model trained to minimize a ranking loss.”
Multi-task deep neural network for multi-label learning (2013, methodology): “Methods Hamming Loss BP-MLL [7] 0.”
Multi-label Zero-Shot Learning with Structured Knowledge Graphs (2017, methodology): “As non-linear embedding approaches, deep neural networks have also been utilized for multi-label classification [50, 34, 18, 46, 45, 49].”
Learning Deep Latent Spaces for Multi-Label Classification (2017, methodology): “While such capabilities were introduced in BP-MLL and CNN-RNN via linear embedding, our approach still produced promising performances among all DNN methods considered.”
Ensemble application of convolutional and recurrent neural networks for multi-label text categorization (2017, unknown): “[29] proposes a BP-MLL that utilizes a full-connected neural network and a pairwise ranking loss function to tackle this task.”
Large Margin Metric Learning for Multi-Label Prediction (2015, methodology): “Several methods (Zhang and Zhou 2006; 2007; Brinker and Hullermeier 2007) fall into the AA category.”
Personalized Deep Learning for Tag Recommendation (2017, methodology): “It is also compared to the non-personalized models including most popluar tags(MP) [6], the multilabel neural networks (BP-MLLs) [24] that have low-level visual features as the input (CH-BPMLL, CM55-BPMLL), CNNs obtained for image annotation which optimizes the pairwise ranking loss to learn the par”