{"list":"other","total":51,"rows":[{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1703.08475","title":"Overcoming Catastrophic Forgetting by Incremental Moment Matching","created":"2017-03-24","cited_by_count":243},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"2006.14769","title":"Supermasks in Superposition","created":"2020-06-26","cited_by_count":227},{"id":"2002.10211","title":"Mnemonics Training: Multi-Class Incremental Learning without Forgetting","created":"2020-02-24","cited_by_count":221},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"1904.02232","title":"BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis","created":"2019-04-03","cited_by_count":176},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91},{"id":"2104.05489","title":"Continual Learning for Text Classification with Information Disentanglement Based Regularization","created":"2021-04-12","cited_by_count":86},{"id":"2012.15504","title":"Continual Learning in Task-Oriented Dialogue Systems","created":"2020-12-31","cited_by_count":83},{"id":"2211.12701","title":"Continual Learning of Natural Language Processing Tasks: A Survey","created":"2022-11-23","cited_by_count":83},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82},{"id":"2112.10017","title":"Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks","created":"2021-12-18","cited_by_count":81},{"id":"2211.02633","title":"A Theoretical Study on Solving Continual Learning","created":"2022-11-04","cited_by_count":80},{"id":"1710.10368","title":"Deep Generative Dual Memory Network for Continual Learning","created":"2017-10-28","cited_by_count":59},{"id":"2211.00789","title":"Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer","created":"2022-11-01","cited_by_count":59},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53},{"id":"1705.08395","title":"Continual Learning in Generative Adversarial Nets","created":"2017-05-23","cited_by_count":51},{"id":"1903.04566","title":"Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay","created":"2019-03-11","cited_by_count":51},{"id":"2010.02500","title":"Efficient Meta Lifelong-Learning with Limited Memory","created":"2020-10-06","cited_by_count":48},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47},{"id":"2112.03271","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","created":"2021-12-06","cited_by_count":46},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44},{"id":"2306.14775","title":"Parameter-Level Soft-Masking for Continual Learning","created":"2023-06-26","cited_by_count":40},{"id":"2106.00829","title":"ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining","created":"2021-06-01","cited_by_count":38},{"id":"2203.10652","title":"Continual Sequence Generation with Adaptive Compositional Modules","created":"2022-03-20","cited_by_count":31},{"id":"1807.06517","title":"Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing","created":"2018-07-17","cited_by_count":29},{"id":"2306.12646","title":"Learnability and Algorithm for Continual Learning","created":"2023-06-22","cited_by_count":28},{"id":"2203.08512","title":"ConTinTin: Continual Learning from Task Instructions","created":"2022-03-16","cited_by_count":26},{"id":"2010.01791","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","created":"2020-10-05","cited_by_count":23},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11}],"next_cursor":null}