Reading List for Machine Learning Paradigms

Semi/Self-Supervised Learning

• Semi-supervised Sequence Learning, Neurips 2015
  https://arxiv.org/pdf/1511.01432.pdf
• Self-supervised Learning for Large-scale Item Recommendations
  https://dl.acm.org/doi/pdf/10.1145/3459637.3481952

Contrastive Learning

• Representation Learning with Contrastive Predictive Coding
  https://arxiv.org/pdf/1807.03748.pdf
• Learning Transferable Visual Models From Natural Language Supervision
  http://proceedings.mlr.press/v139/radford21a

Metric Learning

• Semi-Supervised Learning for Cross-Domain Recommendation to Cold-Start Users
  https://dl.acm.org/doi/10.1145/3357384.3357914
• ArcFace: Additive Angular Margin Loss for Deep Face Recognition
  https://arxiv.org/abs/1801.07698

Transfer Learning

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  https://arxiv.org/abs/1810.04805
• AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE
  https://arxiv.org/abs/2010.11929

Meta-Learning

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
  https://arxiv.org/abs/1703.03400
• Learning to learn by gradient descent by gradient descent
  https://arxiv.org/abs/1606.04474

Multi-task Learning

• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
  https://arxiv.org/abs/1705.07115
• UniT: Multimodal Multitask Learning with a Unified Transformer
  https://arxiv.org/abs/2102.10772

Imbalanced/Long-tail Learning

• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
  https://arxiv.org/abs/1906.07413
• Rethinking the Value of Labels for Improving Class-Imbalanced Learning
  https://arxiv.org/abs/2006.07529

Few-shot Learning

• Meta-Learning for Semi-Supervised Few-Shot Classification
  https://arxiv.org/abs/1803.00676
• Learning to Compare: Relation Network for Few-Shot Learning
  https://arxiv.org/abs/1711.06025v2

Adversarial Learning

• Generative Adversarial Networks
  https://arxiv.org/abs/1406.2661
• Adversarial Training Methods for Semi-Supervised Text Classification
  https://arxiv.org/abs/1605.07725

Robust Learning

• Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
  https://arxiv.org/abs/1609.03683
• Graph convolutional networks for learning with few clean and many noisy labels
  https://arxiv.org/abs/1910.00324

Active Learning

• Learning Algorithms for Active Learning
  https://arxiv.org/abs/1708.00088
• Learning Loss for Active Learning
  https://arxiv.org/abs/1905.03677

Federated Learning

• Communication-Efficient Learning of Deep Networks from Decentralized Data
  https://arxiv.org/abs/1602.05629
• Inverting Gradients - How easy is it to break privacy in federated learning?
  https://arxiv.org/abs/2003.140530

Anomaly Detection

• Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
  https://dl.acm.org/doi/10.1145/3292500.3330672
• On the Value of Out-of-Distribution Testing: An Example of Goodhart’s Law
  https://arxiv.org/abs/2005.09241