Linked Adapters: Linking Past and Future to Present for Effective Continual Learning

• URL: http://arxiv.org/abs/2412.10687v1
• Date: Sat, 14 Dec 2024 05:25:17 GMT
• Title: Linked Adapters: Linking Past and Future to Present for Effective Continual Learning
• Authors: Dupati Srikar Chandra, P. K. Srijith, Dana Rezazadegan, Chris McCarthy,
• Abstract summary: Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. Deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while learning a new task. We propose a novel approach that allows knowledge transfer through a weighted attention mechanism to other task-specific adapters.
• Score: 3.7166121807265045
• License:
• Abstract: Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while learning a new task. Moreover, retraining large models like transformers from scratch for every new task is costly. An effective approach to address continual learning is to use a large pre-trained model with task-specific adapters to adapt to the new tasks. Though this approach can mitigate catastrophic forgetting, they fail to transfer knowledge across tasks as each task is learning adapters separately. To address this, we propose a novel approach Linked Adapters that allows knowledge transfer through a weighted attention mechanism to other task-specific adapters. Linked adapters use a multi-layer perceptron (MLP) to model the attention weights, which overcomes the challenge of backward knowledge transfer in continual learning in addition to modeling the forward knowledge transfer. During inference, our proposed approach effectively leverages knowledge transfer through MLP-based attention weights across all the lateral task adapters. Through numerous experiments conducted on diverse image classification datasets, we effectively demonstrated the improvement in performance on the continual learning tasks using Linked Adapters.

Related papers

• Auto-selected Knowledge Adapters for Lifelong Person Re-identification [54.42307214981537]
  Lifelong Person Re-Identification requires systems to continually learn from non-overlapping datasets across different times and locations. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting. We introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning.
  arXiv  Detail & Related papers  (2024-05-29T11:42:02Z)
• I2I: Initializing Adapters with Improvised Knowledge [15.452979531094567]
  Improvise for. I2LiI, a continual learning algorithm, initializes Adapters for incoming tasks by distilling. previously-learned tasks. I2I consistently achieves better task accuracy than independently-trained Adapters.
  arXiv  Detail & Related papers  (2023-04-04T23:51:48Z)
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties [4.109784267309124]
  Key challenge in continual learning is catastrophic forgetting. We propose a new method, named Online Continual Learning via the Knowledge Invariant and Spread-out Properties (OCLKISP) We empirically evaluate our proposed method on four popular benchmarks for continual learning: Split CIFAR 100, Split SVHN, Split CUB200 and Split Tiny-Image-Net.
  arXiv  Detail & Related papers  (2023-02-02T04:03:38Z)
• Continual Prompt Tuning for Dialog State Tracking [58.66412648276873]
  A desirable dialog system should be able to continually learn new skills without forgetting old ones. We present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks.
  arXiv  Detail & Related papers  (2022-03-13T13:22:41Z)
• Fully Online Meta-Learning Without Task Boundaries [80.09124768759564]
  We study how meta-learning can be applied to tackle online problems of this nature. We propose a Fully Online Meta-Learning (FOML) algorithm, which does not require any ground truth knowledge about the task boundaries. Our experiments show that FOML was able to learn new tasks faster than the state-of-the-art online learning methods.
  arXiv  Detail & Related papers  (2022-02-01T07:51:24Z)
• Adaptive Transfer Learning on Graph Neural Networks [4.233435459239147]
  Graph neural networks (GNNs) are widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph representation. We propose a new transfer learning paradigm on GNNs which could effectively leverage self-supervised tasks as auxiliary tasks to help the target task.
  arXiv  Detail & Related papers  (2021-07-19T11:46:28Z)
• 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)
• Meta-learning the Learning Trends Shared Across Tasks [123.10294801296926]
  Gradient-based meta-learning algorithms excel at quick adaptation to new tasks with limited data. Existing meta-learning approaches only depend on the current task information during the adaptation. We propose a 'Path-aware' model-agnostic meta-learning approach.
  arXiv  Detail & Related papers  (2020-10-19T08:06:47Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)
• AdapterFusion: Non-Destructive Task Composition for Transfer Learning [104.9639614787314]
  Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks. We propose AdapterFusion, a new two stage learning algorithm that leverages knowledge from multiple tasks. We show that our approach outperforms traditional strategies such as full fine-tuning as well as multi-task learning.
  arXiv  Detail & Related papers  (2020-05-01T07:03:42Z)

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.