Meta-Learning

PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators NeurIPS 2021 Personalized Adaptive Meta Learning for Cold-start User Preference Prediction AAAI 2021 Physarum Powered Differentiable Linear Programming Layers and Applications AAAI 2021 Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning IJCAI 2021 Posterior Meta-Replay for Continual Learning NeurIPS 2021 Power Constrained Bandits MLHC 2021 Preference-Adaptive Meta-Learning for Cold-Start Recommendation IJCAI 2021 PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation AAAI 2021 Pre-training with Meta Learning for Chinese Word Segmentation NAACL 2021 Probabilistic task modelling for meta-learning UAI 2021 Progressive Feature Interaction Search for Deep Sparse Network NeurIPS 2021 PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning ACL 2021 Provable Meta-Learning of Linear Representations ICML 2021 Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature NeurIPS 2021 Provably Faster Algorithms for Bilevel Optimization NeurIPS 2021 Pure Exploration in Kernel and Neural Bandits NeurIPS 2021 RankNAS: Efficient Neural Architecture Search by Pairwise Ranking EMNLP 2021 RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving ICCV 2021 Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets ICLR 2021 Rational LAMOL: A Rationale-based Lifelong Learning Framework ACL 2021 Recomposing the Reinforcement Learning Building Blocks with Hypernetworks ICML 2021 Regularising Knowledge Transfer by Meta Functional Learning IJCAI 2021 Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization NeurIPS 2021 Rethinking Bi-Level Optimization in Neural Architecture Search: A Gibbs Sampling Perspective AAAI 2021 Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach EMNLP 2021