Continual Learning

Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning NeurIPS 2022 SparCL: Sparse Continual Learning on the Edge NeurIPS 2022 S-Prompts Learning with Pre-trained Transformers: An Occam’s Razor for Domain Incremental Learning NeurIPS 2022 Static-Dynamic Co-teaching for Class-Incremental 3D Object Detection AAAI 2022 Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams IJCAI 2022 StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models ICML 2022 Structure Learning-Based Task Decomposition for Reinforcement Learning in Non-stationary Environments AAAI 2022 Subspace Regularizers for Few-Shot Class Incremental Learning ICLR 2022 Surpassing the Human Accuracy: Detecting Gallbladder Cancer From USG Images With Curriculum Learning CVPR 2022 Task-Free Continual Learning via Online Discrepancy Distance Learning NeurIPS 2022 TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models EMNLP 2022 The Primacy Bias in Deep Reinforcement Learning ICML 2022 TimeLMs: Diachronic Language Models from Twitter ACL 2022 Towards an Understanding of Default Policies in Multitask Policy Optimization AISTATS 2022 Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector CVPR 2022 Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement EMNLP 2022 Tracking Functional Changes in Nonstationary Signals with Evolutionary Ensemble Bayesian Model for Robust Neural Decoding NeurIPS 2022 Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU EMNLP 2022 TRGP: Trust Region Gradient Projection for Continual Learning ICLR 2022 Type-Driven Multi-Turn Corrections for Grammatical Error Correction ACL 2022 Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification NeurIPS 2022 Unifying Importance Based Regularisation Methods for Continual Learning AISTATS 2022 Unseen Classes at a Later Time? No Problem CVPR 2022 Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models Interspeech 2022 Variational Continual Proxy-Anchor for Deep Metric Learning AISTATS 2022