AAAI 2018 accepted papers on Label-efficient and robust learning
172 of the 937 papers accepted at AAAI 2018 (18.4%) are on Label-efficient and robust learning, compared with 15.6% at AAAI 2017. They fall into 6 topics.
See AAAI 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Recognition and long-tail · 124 papers
- Deep Learning for Case-Based Reasoning Through Prototypes: A Neural Network That Explains Its Predictions (581 citations)
- Style Transfer in Text: Exploration and Evaluation (480 citations)
- Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification (431 citations)
- ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation (332 citations)
- Augmenting End-to-End Dialogue Systems With Commonsense Knowledge (309 citations)
- Structural Deep Embedding for Hyper-Networks (235 citations)
- StarSpace: Embed All The Things! (225 citations)
- Attention-Based Transactional Context Embedding for Next-Item Recommendation (222 citations)
- Who Said What: Modeling Individual Labelers Improves Classification (207 citations)
- Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis (200 citations)
- Partial Multi-Label Learning (198 citations)
- Recurrent Attentional Reinforcement Learning for Multi-Label Image Recognition (174 citations)
and 112 more in the interactive map.
Domain adaptation and generalization · 19 papers
- Learning to Generalize: Meta-Learning for Domain Generalization (1,382 citations)
- Multi-Adversarial Domain Adaptation (941 citations)
- Wasserstein Distance Guided Representation Learning for Domain Adaptation (937 citations)
- Domain Generalization via Conditional Invariant Representations (201 citations)
- Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification (165 citations)
- Unsupervised Domain Adaptation With Distribution Matching Machines (117 citations)
- Personalizing a Dialogue System With Transfer Reinforcement Learning (113 citations)
- Less-Forgetful Learning for Domain Expansion in Deep Neural Networks (77 citations)
- Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization (69 citations)
- Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation (53 citations)
- Neural Networks Incorporating Dictionaries for Chinese Word Segmentation (48 citations)
- Cross-Domain Human Parsing via Adversarial Feature and Label Adaptation (35 citations)
and 7 more in the interactive map.
Semi-supervised learning · 13 papers
- Adversarial Dropout for Supervised and Semi-Supervised Learning (167 citations)
- DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction (158 citations)
- Learning From Semi-Supervised Weak-Label Data (54 citations)
- Inferring Emotion from Conversational Voice Data: A Semi-Supervised Multi-Path Generative Neural Network Approach (43 citations)
- Semi-Supervised Learning From Crowds Using Deep Generative Models (38 citations)
- RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding (36 citations)
- Semi-Supervised Biomedical Translation With Cycle Wasserstein Regression GANs (35 citations)
- Semi-Supervised AUC Optimization Without Guessing Labels of Unlabeled Data (24 citations)
- Semi-Supervised Bayesian Attribute Learning for Person Re-Identification (24 citations)
- A General Formulation for Safely Exploiting Weakly Supervised Data (12 citations)
- ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-Label Classification (12 citations)
- Selective Verification Strategy for Learning From Crowds (3 citations)
and 1 more in the interactive map.
Zero-/few-shot and meta-learning · 9 papers
- Generalizing and Improving Bilingual Word Embedding Mappings with a Multi-Step Framework of Linear Transformations (218 citations)
- Zero-Shot Learning via Class-Conditioned Deep Generative Models (138 citations)
- Meta Multi-Task Learning for Sequence Modeling (88 citations)
- Zero-Shot Learning With Attribute Selection (36 citations)
- Joint Dictionaries for Zero-Shot Learning (25 citations)
- Co-Domain Embedding Using Deep Quadruplet Networks for Unseen Traffic Sign Recognition (23 citations)
- Towards Affordable Semantic Searching: Zero-Shot Retrieval via Dominant Attributes (21 citations)
- Adversarial Zero-shot Learning With Semantic Augmentation (20 citations)
- Deep Semantic Structural Constraints for Zero-Shot Learning (20 citations)
Knowledge distillation · 4 papers
- Exercise-Enhanced Sequential Modeling for Student Performance Prediction (278 citations)
- DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer (217 citations)
- Learning With Single-Teacher Multi-Student (25 citations)
- Proposition Entailment in Educational Applications using Deep Neural Networks (3 citations)
Noisy labels · 3 papers
- Reinforcement Learning for Relation Classification From Noisy Data (354 citations)
- Deep Learning from Crowds (201 citations)
- Overlap-Robust Decision Boundary Learning for Within-Network Classification (2 citations)
