Contrastive Continual Learning with Feature Propagation
- URL: http://arxiv.org/abs/2112.01713v1
- Date: Fri, 3 Dec 2021 04:55:28 GMT
- Title: Contrastive Continual Learning with Feature Propagation
- Authors: Xuejun Han, Yuhong Guo
- Abstract summary: Continual machine learners are elaborated to commendably learn a stream of tasks with domain and class shifts among different tasks.
We propose a general feature-propagation based contrastive continual learning method which is capable of handling multiple continual learning scenarios.
- Score: 32.70482982044965
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Classical machine learners are designed only to tackle one task without
capability of adopting new emerging tasks or classes whereas such capacity is
more practical and human-like in the real world. To address this shortcoming,
continual machine learners are elaborated to commendably learn a stream of
tasks with domain and class shifts among different tasks. In this paper, we
propose a general feature-propagation based contrastive continual learning
method which is capable of handling multiple continual learning scenarios.
Specifically, we align the current and previous representation spaces by means
of feature propagation and contrastive representation learning to bridge the
domain shifts among distinct tasks. To further mitigate the class-wise shifts
of the feature representation, a supervised contrastive loss is exploited to
make the example embeddings of the same class closer than those of different
classes. The extensive experimental results demonstrate the outstanding
performance of the proposed method on six continual learning benchmarks
compared to a group of cutting-edge continual learning methods.
Related papers
- 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) - Inferring Versatile Behavior from Demonstrations by Matching Geometric
Descriptors [72.62423312645953]
Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps.
Current Imitation Learning algorithms often only consider unimodal expert demonstrations and act in a state-action-based setting.
Instead, we combine a mixture of movement primitives with a distribution matching objective to learn versatile behaviors that match the expert's behavior and versatility.
arXiv Detail & Related papers (2022-10-17T16:42:59Z) - 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) - On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
arXiv Detail & Related papers (2022-03-08T09:57:48Z) - Co$^2$L: Contrastive Continual Learning [69.46643497220586]
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks.
We propose a rehearsal-based continual learning algorithm that focuses on continually learning and maintaining transferable representations.
arXiv Detail & Related papers (2021-06-28T06:14:38Z) - Conditional Meta-Learning of Linear Representations [57.90025697492041]
Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks.
In this work we overcome this issue by inferring a conditioning function, mapping the tasks' side information into a representation tailored to the task at hand.
We propose a meta-algorithm capable of leveraging this advantage in practice.
arXiv Detail & Related papers (2021-03-30T12:02:14Z) - Learning Invariant Representation for Continual Learning [5.979373021392084]
A key challenge in Continual learning is catastrophically forgetting previously learned tasks when the agent faces a new one.
We propose a new pseudo-rehearsal-based method, named learning Invariant Representation for Continual Learning (IRCL)
Disentangling the shared invariant representation helps to learn continually a sequence of tasks, while being more robust to forgetting and having better knowledge transfer.
arXiv Detail & Related papers (2021-01-15T15:12:51Z) - Incremental Embedding Learning via Zero-Shot Translation [65.94349068508863]
Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks.
We propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI)
In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks.
arXiv Detail & Related papers (2020-12-31T08:21:37Z) - A Survey on Contrastive Self-supervised Learning [0.0]
Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets.
Contrastive learning has recently become a dominant component in self-supervised learning methods for computer vision, natural language processing (NLP), and other domains.
This paper provides an extensive review of self-supervised methods that follow the contrastive approach.
arXiv Detail & Related papers (2020-10-31T21:05:04Z) - Importance Weighted Policy Learning and Adaptation [89.46467771037054]
We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning.
The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior.
Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
arXiv Detail & Related papers (2020-09-10T14:16:58Z)
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.