The Effect of Task Ordering in Continual Learning
- URL: http://arxiv.org/abs/2205.13323v1
- Date: Thu, 26 May 2022 12:56:15 GMT
- Title: The Effect of Task Ordering in Continual Learning
- Authors: Samuel J. Bell and Neil D. Lawrence
- Abstract summary: We show that reordering tasks significantly affects the amount of catastrophic forgetting.
We show that the effect of task ordering can be exploited to modify continual learning performance.
- Score: 12.571389210876315
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We investigate the effect of task ordering on continual learning performance.
We conduct an extensive series of empirical experiments on synthetic and
naturalistic datasets and show that reordering tasks significantly affects the
amount of catastrophic forgetting. Connecting to the field of curriculum
learning, we show that the effect of task ordering can be exploited to modify
continual learning performance, and present a simple approach for doing so. Our
method computes the distance between all pairs of tasks, where distance is
defined as the source task curvature of a gradient step toward the target task.
Using statistically rigorous methods and sound experimental design, we show
that task ordering is an important aspect of continual learning that can be
modified for improved performance.
Related papers
- Instruction Matters, a Simple yet Effective Task Selection Approach in Instruction Tuning for Specific Tasks [51.15473776489712]
We show that leveraging instruction information textitalone enables the identification of pertinent tasks for instruction tuning.
By learning the unique instructional template style of the meta-dataset, we observe an improvement in task selection accuracy.
Experimental results demonstrate that training on a small set of tasks, chosen solely based on the instructions, leads to substantial performance improvements.
arXiv Detail & Related papers (2024-04-25T08:49:47Z) - Data-CUBE: Data Curriculum for Instruction-based Sentence Representation
Learning [85.66907881270785]
We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training.
In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk.
In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
arXiv Detail & Related papers (2024-01-07T18:12:20Z) - Efficient Rehearsal Free Zero Forgetting Continual Learning using
Adaptive Weight Modulation [3.6683171094134805]
Continual learning involves acquiring knowledge of multiple tasks over an extended period.
Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks.
Our approach attempts to maximize the performance of the new task, while ensuring zero forgetting.
arXiv Detail & Related papers (2023-11-26T12:36:05Z) - An Exploration of Data Efficiency in Intra-Dataset Task Transfer for
Dialog Understanding [65.75873687351553]
This study explores the effects of varying quantities of target task training data on sequential transfer learning in the dialog domain.
Unintuitively, our data shows that often target task training data size has minimal effect on how sequential transfer learning performs compared to the same model without transfer learning.
arXiv Detail & Related papers (2022-10-21T04:36:46Z) - Task Formulation Matters When Learning Continually: A Case Study in
Visual Question Answering [58.82325933356066]
Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge.
We present a detailed study of how different settings affect performance for Visual Question Answering.
arXiv Detail & Related papers (2022-09-30T19:12:58Z) - Leveraging convergence behavior to balance conflicting tasks in
multi-task learning [3.6212652499950138]
Multi-Task Learning uses correlated tasks to improve performance generalization.
Tasks often conflict with each other, which makes it challenging to define how the gradients of multiple tasks should be combined.
We propose a method that takes into account temporal behaviour of the gradients to create a dynamic bias that adjust the importance of each task during the backpropagation.
arXiv Detail & Related papers (2022-04-14T01:52:34Z) - Variational Multi-Task Learning with Gumbel-Softmax Priors [105.22406384964144]
Multi-task learning aims to explore task relatedness to improve individual tasks.
We propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks.
arXiv Detail & Related papers (2021-11-09T18:49:45Z) - Efficiently Identifying Task Groupings for Multi-Task Learning [55.80489920205404]
Multi-task learning can leverage information learned by one task to benefit the training of other tasks.
We suggest an approach to select which tasks should train together in multi-task learning models.
Our method determines task groupings in a single training run by co-training all tasks together and quantifying the effect to which one task's gradient would affect another task's loss.
arXiv Detail & Related papers (2021-09-10T02:01:43Z)
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.