اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدOnline Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
124
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new (out-of-distribution) tasks, while also requiring fast remembering. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. We empirically show that Continual-MAML is better suited to the new scenario than the aforementioned methodologies, as well as standard continual learning and meta-learning approaches.
قيم البحث
اقرأ أيضاً
Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be adapted to t
he specificity of the pervasive domain. In particular, issues related to continual learning need to be addressed. In this paper, we present a distillation-based approach dealing with catastrophic forgetting in federated learning scenario. Specifically, Human Activity Recognition tasks are used as a demonstration domain.
This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning efficiency an
d generalisability. More specifically, the proposed approach fixes the autopilot structure as typical three-loop autopilot and deep reinforcement learning is utilised to learn the autopilot gains. To solve the flight control problem, we then formulate a Markovian decision process with a proper reward function that enable the application of reinforcement learning theory. Another type of domain knowledge is exploited for defining the reward function, by shaping reference inputs in consideration of important control objectives and using the shaped reference inputs in the reward function. The state-of-the-art deep deterministic policy gradient algorithm is utilised to learn an action policy that maps the observed states to the autopilot gains. Extensive empirical numerical simulations are performed to validate the proposed computational control algorithm.
With the rapid development of deep learning, deep reinforcement learning (DRL) began to appear in the field of resource scheduling in recent years. Based on the previous research on DRL in the literature, we introduce online resource scheduling algor
ithm DeepRM2 and the offline resource scheduling algorithm DeepRM_Off. Compared with the state-of-the-art DRL algorithm DeepRM and heuristic algorithms, our proposed algorithms have faster convergence speed and better scheduling efficiency with regarding to average slowdown time, job completion time and rewards.
Models trained with offline data often suffer from continual distribution shifts and expensive labeling in changing environments. This calls for a new online learning paradigm where the learner can continually adapt to changing environments with limi
ted labels. In this paper, we propose a new online setting -- Online Active Continual Adaptation, where the learner aims to continually adapt to changing distributions using both unlabeled samples and active queries of limited labels. To this end, we propose Online Self-Adaptive Mirror Descent (OSAMD), which adopts an online teacher-student structure to enable online self-training from unlabeled data, and a margin-based criterion that decides whether to query the labels to track changing distributions. Theoretically, we show that, in the separable case, OSAMD has an $O({T}^{1/2})$ dynamic regret bound under mild assumptions, which is even tighter than the lower bound $Omega(T^{2/3})$ of traditional online learning with full labels. In the general case, we show a regret bound of $O({alpha^*}^{1/3} {T}^{2/3} + alpha^* T)$, where $alpha^*$ denotes the separability of domains and is usually small. Our theoretical results show that OSAMD can fast adapt to changing environments with active queries. Empirically, we demonstrate that OSAMD achieves favorable regrets under changing environments with limited labels on both simulated and real-world data, which corroborates our theoretical findings.
Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the problem of
continual domain adaptation, where the model is presented with a labeled source domain and a sequence of unlabeled target domains. There are two major obstacles in this problem: domain shifts and catastrophic forgetting. In this work, we propose Gradient Regularized Contrastive Learning to solve the above obstacles. At the core of our method, gradient regularization plays two key roles: (1) enforces the gradient of contrastive loss not to increase the supervised training loss on the source domain, which maintains the discriminative power of learned features; (2) regularizes the gradient update on the new domain not to increase the classification loss on the old target domains, which enables the model to adapt to an in-coming target domain while preserving the performance of previously observed domains. Hence our method can jointly learn both semantically discriminative and domain-invariant features with labeled source domain and unlabeled target domains. The experiments on Digits, DomainNet and Office-Caltech benchmarks demonstrate the strong performance of our approach when compared to the state-of-the-art.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
