RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning

• URL: http://arxiv.org/abs/2205.10857v1
• Date: Sun, 22 May 2022 15:52:35 GMT
• Title: RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning
• Authors: Han Wang, Ruiliu Fu, Xuejun Zhang, Jun Zhou
• Abstract summary: Lifelong Language Learning (LLL) aims to train a neural network to learn a stream of NLP tasks while retaining knowledge from previous tasks. Previous works which followed data-free constraint still suffer from catastrophic forgetting issue. We propose the residual variational autoencoder (RVAE) to enhance LAMOL, a recent LLL model, by mapping different tasks into a limited unified semantic space.
• Score: 13.946029695618018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lifelong Language Learning (LLL) aims to train a neural network to learn a stream of NLP tasks while retaining knowledge from previous tasks. However, previous works which followed data-free constraint still suffer from catastrophic forgetting issue, where the model forgets what it just learned from previous tasks. In order to alleviate catastrophic forgetting, we propose the residual variational autoencoder (RVAE) to enhance LAMOL, a recent LLL model, by mapping different tasks into a limited unified semantic space. In this space, previous tasks are easy to be correct to their own distribution by pseudo samples. Furthermore, we propose an identity task to make the model is discriminative to recognize the sample belonging to which task. For training RVAE-LAMOL better, we propose a novel training scheme Alternate Lag Training. In the experiments, we test RVAE-LAMOL on permutations of three datasets from DecaNLP. The experimental results demonstrate that RVAE-LAMOL outperforms na\"ive LAMOL on all permutations and generates more meaningful pseudo-samples.

Related papers

• Continual learning with task specialist [2.8830182365988923]
  We propose Continual Learning with Task Specialists (CLTS) to address the issues of catastrophic forgetting and limited labelled data. The model consists of Task Specialists (T S) and Task Predictor (T P) with pre-trained Stable Diffusion (SD) module. A comparison study with four SOTA models conducted on three real-world datasets shows that the proposed model outperforms all the selected baselines.
  arXiv  Detail & Related papers  (2024-09-26T12:59:09Z)
• Meta-Tasks: An alternative view on Meta-Learning Regularization [17.738450255829633]
  This paper proposes a novel solution that can generalize to both training and novel tasks while also utilizing unlabeled samples. The experimental results show that the proposed method outperforms prototypical networks by 3.9%.
  arXiv  Detail & Related papers  (2024-02-27T21:15:40Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)
• How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? [92.90857135952231]
  Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities. We study ICL in one of its simplest setups: pretraining a linearly parameterized single-layer linear attention model for linear regression.
  arXiv  Detail & Related papers  (2023-10-12T15:01:43Z)
• Language Reward Modulation for Pretraining Reinforcement Learning [61.76572261146311]
  We propose leveraging the capabilities of LRFs as a pretraining signal for reinforcement learning. Our VLM pretraining approach, which is a departure from previous attempts to use LRFs, can warmstart sample-efficient learning on robot manipulation tasks.
  arXiv  Detail & Related papers  (2023-08-23T17:37:51Z)
• Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue [80.05509768165135]
  generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. Most existing generative replay methods use only a single task-specific token to control their models. We propose a novel method, prompt conditioned VAE for lifelong learning, to enhance generative replay by incorporating tasks' statistics.
  arXiv  Detail & Related papers  (2022-10-14T13:12:14Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Lifelong Learning of Few-shot Learners across NLP Tasks [45.273018249235705]
  We study the challenge of lifelong learning to few-shot learn over a sequence of diverse NLP tasks. We propose a continual meta-learning approach which learns to generate adapter weights from a few examples. We demonstrate our approach preserves model performance over training tasks and leads to positive knowledge transfer when the future tasks are learned.
  arXiv  Detail & Related papers  (2021-04-18T10:41:56Z)
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification [8.998976678920236]
  We propose a tAsk-auGmented actIve meta-LEarning (AGILE) method to efficiently adapt Deep Neural Networks to new tasks. AGILE combines a meta-learning algorithm with a novel task augmentation technique which we use to generate an initial adaptive model. We show that the proposed task-augmented meta-learning framework can learn to classify new cell types after a single gradient step.
  arXiv  Detail & Related papers  (2020-07-09T18:03:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.