ترغب بنشر مسار تعليمي؟ اضغط هنا

Lifelong Learning with Sketched Structural Regularization

77   0   0.0 ( 0 )
 نشر من قبل Jingfeng Wu
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithms that mitigate catastrophic forgetting by penalizing the network for changing its critical parameters from previous tasks while learning a new one. The penalty is often induced via a quadratic regularizer defined by an emph{importance matrix}, e.g., the (empirical) Fisher information matrix in the Elastic Weight Consolidation framework. In practice and due to computational constraints, most SR methods crudely approximate the importance matrix by its diagonal. In this paper, we propose emph{Sketched Structural Regularization} (Sketched SR) as an alternative approach to compress the importance matrices used for regularizing in SR methods. Specifically, we apply emph{linear sketching methods} to better approximate the importance matrices in SR algorithms. We show that sketched SR: (i) is computationally efficient and straightforward to implement, (ii) provides an approximation error that is justified in theory, and (iii) is method oblivious by construction and can be adapted to any method that belongs to the structural regularization class. We show that our proposed approach consistently improves various SR algorithms performance on both synthetic experiments and benchmark continual learning tasks, including permuted-MNIST and CIFAR-100.



قيم البحث

اقرأ أيضاً

Graph neural networks (GNNs) are powerful models for many graph-structured tasks. Existing models often assume that a complete structure of a graph is available during training, however, in practice, graph-structured data is usually formed in a strea ming fashion, so that learning a graph continuously is often necessary. In this paper, we aim to bridge GNN to lifelong learning by converting a graph problem to a regular learning problem, so that GNN is able to inherit the lifelong learning techniques developed for convolutional neural networks (CNNs). To this end, we propose a new graph topology based on feature cross-correlation, called the feature graph. It takes features as new nodes and turns nodes into independent graphs. This successfully converts the original problem of node classification to graph classification, in which the increasing nodes are turned into independent training samples. In the experiments, we demonstrate the efficiency and effectiveness of feature graph networks (FGN) by continuously learning a sequence of classical graph datasets. We also show that FGN achieves superior performance in human action recognition with distributed streaming signals for wearable devices.
A central capability of a long-lived reinforcement learning (RL) agent is to incrementally adapt its behavior as its environment changes, and to incrementally build upon previous experiences to facilitate future learning in real-world scenarios. In t his paper, we propose LifeLong Incremental Reinforcement Learning (LLIRL), a new incremental algorithm for efficient lifelong adaptation to dynamic environments. We develop and maintain a library that contains an infinite mixture of parameterized environment models, which is equivalent to clustering environment parameters in a latent space. The prior distribution over the mixture is formulated as a Chinese restaurant process (CRP), which incrementally instantiates new environment models without any external information to signal environmental changes in advance. During lifelong learning, we employ the expectation maximization (EM) algorithm with online Bayesian inference to update the mixture in a fully incremental manner. In EM, the E-step involves estimating the posterior expectation of environment-to-cluster assignments, while the M-step updates the environment parameters for future learning. This method allows for all environment models to be adapted as necessary, with new models instantiated for environmental changes and old models retrieved when previously seen environments are encountered again. Experiments demonstrate that LLIRL outperforms relevant existing methods, and enables effective incremental adaptation to various dynamic environments for lifelong learning.
82 - Fei Ye , Adrian G. Bors 2021
A unique cognitive capability of humans consists in their ability to acquire new knowledge and skills from a sequence of experiences. Meanwhile, artificial intelligence systems are good at learning only the last given task without being able to remem ber the databases learnt in the past. We propose a novel lifelong learning methodology by employing a Teacher-Student network framework. While the Student module is trained with a new given database, the Teacher module would remind the Student about the information learnt in the past. The Teacher, implemented by a Generative Adversarial Network (GAN), is trained to preserve and replay past knowledge corresponding to the probabilistic representations of previously learn databases. Meanwhile, the Student module is implemented by a Variational Autoencoder (VAE) which infers its latent variable representation from both the output of the Teacher module as well as from the newly available database. Moreover, the Student module is trained to capture both continuous and discrete underlying data representations across different domains. The proposed lifelong learning framework is applied in supervised, semi-supervised and unsupervised training. The code is available~: url{https://github.com/dtuzi123/Lifelong-Teacher-Student-Network-Learning}
Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network by softeni ng the ground-truth labels in the training data in an attempt to penalize overconfident outputs. Existing approaches typically use cross-validation to impose this smoothing, which is uniform across all training data. In this paper, we show that such label smoothing imposes a quantifiable bias in the Bayes error rate of the training data, with regions of the feature space with high overlap and low marginal likelihood having a lower bias and regions of low overlap and high marginal likelihood having a higher bias. These theoretical results motivate a simple objective function for data-dependent smoothing to mitigate the potential negative consequences of the operation while maintaining its desirable properties as a regularizer. We call this approach Structural Label Smoothing (SLS). We implement SLS and empirically validate on synthetic, Higgs, SVHN, CIFAR-10, and CIFAR-100 datasets. The results confirm our theoretical insights and demonstrate the effectiveness of the proposed method in comparison to traditional label smoothing.
Learning interpretable and transferable subpolicies and performing task decomposition from a single, complex task is difficult. Some traditional hierarchical reinforcement learning techniques enforce this decomposition in a top-down manner, while met a-learning techniques require a task distribution at hand to learn such decompositions. This paper presents a framework for using diverse suboptimal world models to decompose complex task solutions into simpler modular subpolicies. This framework performs automatic decomposition of a single source task in a bottom up manner, concurrently learning the required modular subpolicies as well as a controller to coordinate them. We perform a series of experiments on high dimensional continuous action control tasks to demonstrate the effectiveness of this approach at both complex single task learning and lifelong learning. Finally, we perform ablation studies to understand the importance and robustness of different elements in the framework and limitations to this approach.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا