Episodic Memory in Lifelong Language Learning
We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments on text classification and question answering demonstrate the complementary benefits of sparse experience replay and local adaptation to allow the model to continuously learn from new datasets. We also show that the space complexity of the episodic memory module can be reduced significantly (~50-90%) by randomly choosing which examples to store in memory with a minimal decrease in performance. We consider an episodic memory component as a crucial building block of general linguistic intelligence and see our model as a first step in that direction.
Code (2)
Tasks
Continual LearningGeneral ClassificationQuestion Answeringtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Attacking Lifelong Learning Models with Gradient Reversion
Lifelong learning aims at avoiding the catastrophic forgetting problem of traditional supervised learning models. Episodic memory based lifelong learning methods such as A-GEM (Chaudhry et al., 2018b) are s…
Continual LearningLifelong learningImproved Schemes for Episodic Memory-based Lifelong Learning
Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to gradually forget the previous learned kno…
Lifelong learningLifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization
Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of info…
Active LearningContinuous Object RecognitionIncremental LearningLifelong learning+1Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge is that the model would catastrophically …
Event DetectionLifelong learningLearning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data
Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning sc…
Lifelong learningQuestion AnsweringScheduling