AAAI 2016 accepted papers on Label-efficient and robust learning
108 of the 548 papers accepted at AAAI 2016 (19.7%) are on Label-efficient and robust learning. They fall into 7 topics.
See AAAI 2016 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 · 77 papers
- VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback (1,123 citations)
- Deep Hashing Network for Efficient Similarity Retrieval (670 citations)
- Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping (494 citations)
- Unsupervised Feature Selection with Structured Graph Optimization (345 citations)
- On the Performance of GoogLeNet and AlexNet Applied to Sketches (330 citations)
- Gated Neural Networks for Targeted Sentiment Analysis (313 citations)
- Column Sampling Based Discrete Supervised Hashing (301 citations)
- Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference (238 citations)
- Deep Quantization Network for Efficient Image Retrieval (224 citations)
- What Happens Next? Event Prediction Using a Compositional Neural Network Model (196 citations)
- Context-Sensitive Twitter Sentiment Classification Using Neural Network (145 citations)
- Improving Opinion Aspect Extraction Using Semantic Similarity and Aspect Associations (140 citations)
and 65 more in the interactive map.
Domain adaptation and generalization · 13 papers
- Return of Frustratingly Easy Domain Adaptation (2,058 citations)
- A Representation Learning Framework for Multi-Source Transfer Parsing (90 citations)
- Multi-Domain Active Learning for Recommendation (53 citations)
- Transfer Learning for Cross-Language Text Categorization through Active Correspondences Construction (48 citations)
- Cold-Start Heterogeneous-Device Wireless Localization (39 citations)
- ExTaSem! Extending, Taxonomizing and Semantifying Domain Terminologies (22 citations)
- Domain-Constraint Transfer Coding for Imbalanced Unsupervised Domain Adaptation (17 citations)
- Learning by Transferring from Unsupervised Universal Sources (16 citations)
- Spectral Bisection Tree Guided Deep Adaptive Exemplar Autoencoder for Unsupervised Domain Adaptation (16 citations)
- Active Learning with Cross-Class Knowledge Transfer (8 citations)
- A Probabilistic Approach to Knowledge Translation (2 citations)
- Evaluation of Semantic Dependency Labeling Across Domains (1 citation)
and 1 more in the interactive map.
Semi-supervised learning · 9 papers
- SAND: Semi-Supervised Adaptive Novel Class Detection and Classification over Data Stream (177 citations)
- Robust Semi-Supervised Learning through Label Aggregation (57 citations)
- Modeling Evolving Relationships Between Characters in Literary Novels (45 citations)
- Global Distant Supervision for Relation Extraction (37 citations)
- Towards Safe Semi-Supervised Learning for Multivariate Performance Measures (35 citations)
- Semi-Supervised Dictionary Learning via Structural Sparse Preserving (31 citations)
- Acquiring Knowledge of Affective Events from Blogs Using Label Propagation (30 citations)
- Joint Word Segmentation, POS-Tagging and Syntactic Chunking (27 citations)
- Semi-Supervised Multinomial Naive Bayes for Text Classification by Leveraging Word-Level Statistical Constraint (17 citations)
Noisy labels · 4 papers
- Re-Active Learning: Active Learning with Relabeling (61 citations)
- Risk Minimization in the Presence of Label Noise (59 citations)
- Distant IE by Bootstrapping Using Lists and Document Structure (15 citations)
- Learning with Marginalized Corrupted Features and Labels Together (9 citations)
Zero-/few-shot and meta-learning · 3 papers
OOD and anomaly detection · 1 paper
Knowledge distillation · 1 paper
- Face Model Compression by Distilling Knowledge from Neurons (211 citations)
