The Emerging Trends of Multi-Label Learning
arXiv:2011.11197 · doi:10.1109/TPAMI.2021.3119334
Abstract
Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data. For example, extreme multi-label classification is an active and rapidly growing research area that deals with classification tasks with an extremely large number of classes or labels; utilizing massive data with limited supervision to build a multi-label classification model becomes valuable for practical applications, etc. Besides these, there are tremendous efforts on how to harvest the strong learning capability of deep learning to better capture the label dependencies in multi-label learning, which is the key for deep learning to address real-world classification tasks. However, it is noted that there has been a lack of systemic studies that focus explicitly on analyzing the emerging trends and new challenges of multi-label learning in the era of big data. It is imperative to call for a comprehensive survey to fulfill this mission and delineate future research directions and new applications.
arXiv commentAccepted to TPAMI 2021
References in corpus (34)
- Distributed Representations of Words and Phrases and their Compositionality
- Nearly unbiased variable selection under minimax concave penalty
- Deep Visual Domain Adaptation: A Survey
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- The sparsity and bias of the Lasso selection in high-dimensional linear regression
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Large-scale Multi-label Learning with Missing Labels
- A Theoretical Analysis of NDCG Type Ranking Measures
- Large-scale Multi-label Text Classification - Revisiting Neural Networks
- CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
- Beta-Negative Binomial Process and Poisson Factor Analysis
- Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification
- Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
- AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
- Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
- Fast Zero-Shot Image Tagging
- DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
- Order-Free RNN with Visual Attention for Multi-Label Classification
- Maximum Margin Output Coding
- Noisy multi-label semi-supervised dimensionality reduction
- DECAF: Deep Extreme Classification with Label Features
- A no-regret generalization of hierarchical softmax to extreme multi-label classification
- A novel online multi-label classifier for high-speed streaming data applications
- Multi-Label Learning with Deep Forest
- Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
- ECLARE: Extreme Classification with Label Graph Correlations
- Consistent Multilabel Ranking through Univariate Losses
- Large-Scale Multi-Label Learning with Incomplete Label Assignments
- Online Visual Multi-Object Tracking via Labeled Random Finite Set Filtering
- Matrix Co-completion for Multi-label Classification with Missing Features and Labels
- Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
- A Self-paced Regularization Framework for Partial-Label Learning
- Top- eXtreme Contextual Bandits with Arm Hierarchy