This repository contains Curriculum Learning related papers and materials. Welcome contribute to this repo (typos or adding new papers).
- Curriculum Learning [2009]
- First paper about CL
- Bilingual Word Embeddings for Phrase-Based Machine Translation [2013]
- Learning to Execute [2014]
- Self-Paced Curriculum Learning [AAAI]
- Self-paced Learning & CL combined
- Curriculum learning of multiple tasks [CVPR]
- Recurrent neural network language model adaptation with curriculum learning
- CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance
- Easy Questions First? A Case Study on Curriculum Learning for Question Answering [ACL]
- Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning [ACL]
- Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks
- Multi-modal curriculum learning for semisupervised image classification
- Automated Curriculum Learning for Neural Networks [ICML]
- RL related
- Curriculum Learning for Multi-Task Classification of Visual Attributes [ICCV]
- Curriculum Dropout [ICCV]
- Curriculum Learning and Minibatch Bucketing in Neural Machine Translation [RANLP]
- Repeat before forgetting: Spaced repetition for efficient and effective training of neural networks [EMNLP]
- Teacher-Student Curriculum Learning
- Boosting neural machine translation [IJCNLP]
- Curriculum Learning in Reinforcement Learning
- An Empirical Exploration of Curriculum Learning for Neural Machine Translation
- Curriculum Learning by Transfer Learning - Theory and Experiments with Deep Networks [ICML]
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels [ICML]
- Curriculum Learning for Heterogeneous Star Network Embedding via Deep Reinforcement Learning [WSDM]
- Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity [ICLR]
- Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management [ACL]
- LEARNING TO TEACH [ICLR]
- Curriculum Learning for Natural Answer Generation [IJCAI]
- Learning Curriculum Policies for Reinforcement Learning
- Starcraft micromanagement with reinforcement learning and curriculum transfer learning
- Curriculumnet: Weakly supervised learning from large-scale web images [ECCV]
- On The Power of Curriculum Learning in Training Deep Networks [ICML]
- Reinforcement Learning based Curriculum Optimization for Neural Machine Translation [NAACL] [short]
- Dynamic Curriculum Learning for Imbalanced Data Classification
- Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives [ACL]
- Sentence Level Curriculum Learning for Improved Neural Conversational Models [ACL]
- Curriculum Learning for Cumulative Return Maximization [IJCAI]
- RL related
- Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation [ACL]
- Curriculum Learning for Domain Adaptation in Neural Machine Translation [NAACL]
- Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation [BMVC]
- Learning a Multitask Curriculum for Neural Machine Translation
- Self-Attention Enhanced CNNs and Collaborative Curriculum Learning for Distantly Supervised Relation Extraction [EMNLP]
- Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum [NIPS]
- Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Models [AAAI]
- From Few to More: Large-scale Dynamic Multiagent Curriculum Learning [AAAI]
- Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation [AAAI]
- Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning [ICLR]
- Automated curriculum generation through setter-solver interactions [ICLR]
- Curriculum Loss: Robust Learning and Generalization against Label Corruption [ICLR]
- CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation [ACL]
- Curriculum Learning for Natural Language Understanding [ACL]
- Learning a Multi-Domain Curriculum for Neural Machine Translation [ACL]
- Curriculum Pre-training for End-to-End Speech Translation [ACL]
- Norm-Based Curriculum Learning for Neural Machine Translation [ACL]
- Uncertainty-Aware Curriculum Learning for Neural Machine Translation [ACL]
- Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation [IJCAI]
- Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning [IJCAI]
- Automatic Curriculum Learning For Deep RL: A Short Survey [IJCAI]
- Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation [EMNLP]
- SuperLoss: A Generic Loss for Robust Curriculum Learning [NIPS]
- Automatic Curriculum Learning through Value Disagreement [NIPS]
- A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances [NIPS]
- Curriculum By Smoothing [NIPS]
- Curriculum Learning by Dynamic Instance Hardness [NIPS]
- Curriculum learning for multilevel budgeted combinatorial problems [NIPS]
My homepage contains notes(in Chinese) on papers I have read. I may update links of some good notes written by others.
My homepage notes links: Curriculum Learning PaperNote
Curriculum Learning schedule summary: Curriculum Learning schedule 总结