DeepAI AI Chat
Log In Sign Up

Multi-Domain Multi-Task Rehearsal for Lifelong Learning

by   Fan lyu, et al.
University of South Carolina
Tianjin University

Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting of previous knowledge when moving to new tasks. However, the old tasks of the most previous rehearsal-based methods suffer from the unpredictable domain shift when training the new task. This is because these methods always ignore two significant factors. First, the Data Imbalance between the new task and old tasks that makes the domain of old tasks prone to shift. Second, the Task Isolation among all tasks will make the domain shift toward unpredictable directions; To address the unpredictable domain shift, in this paper, we propose Multi-Domain Multi-Task (MDMT) rehearsal to train the old tasks and new task parallelly and equally to break the isolation among tasks. Specifically, a two-level angular margin loss is proposed to encourage the intra-class/task compactness and inter-class/task discrepancy, which keeps the model from domain chaos. In addition, to further address domain shift of the old tasks, we propose an optional episodic distillation loss on the memory to anchor the knowledge for each old task. Experiments on benchmark datasets validate the proposed approach can effectively mitigate the unpredictable domain shift.


page 1

page 2

page 3

page 4


Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

The dynamic expansion architecture is becoming popular in class incremen...

Federated Class-Incremental Learning

Federated learning (FL) has attracted growing attention via data-private...

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

Few-shot Class-Incremental Learning (FSCIL) aims at learning new concept...

Online Deep Metric Learning via Mutual Distillation

Deep metric learning aims to transform input data into an embedding spac...

Learning without Forgetting for 3D Point Cloud Objects

When we fine-tune a well-trained deep learning model for a new set of cl...

Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

Deep learning models suffer from catastrophic forgetting when learning n...

Lifelong Intent Detection via Multi-Strategy Rebalancing

Conventional Intent Detection (ID) models are usually trained offline, w...