Lifelong Learning Methods Research Articles

Sparsify dynamically expandable network via variational dropout

This paper develops a new method for lifelong learning referred to as Sparsify Dynamically Expandable Network (SDEN) via Variational Dropout, which explores a sparse model while preserving the performance. Dynamically Expandable Network (DEN) can learn a sequence of tasks via performing network retraining, network expansion by adding only the necessary neurons, and network split to effectively prevent semantic drift in an online manner. To overcome point estimation of parameters in DEN, Bayesian Compression for DEN is developed under the Bayesian framework. However, this method demands more time for model training and testing. To improve the model efficiency, we propose SDEN under the efficient sparse learning framework. We validate our SDEN in the lifelong learning scenarios with multiple frequently used benchmarks, on which it can obtain comparable classification accuracy, and less training and testing time compared with the comparison methods. Furthermore, our method can also learn a more sparse network structure which means fewer network parameters.

A Lifelong Learning Method Based on Event-Triggered Online Frozen-EWC Transformer Encoder for Equipment Digital Twin Dynamic Evolution

A Lifelong Learning Method Based on Event-Triggered Online Frozen-EWC Transformer Encoder for Equipment Digital Twin Dynamic Evolution

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

Data drift is a thorny challenge when deploying person re-identification (ReID) models into real-world devices, where the data distribution is significantly different from that of the training environment and keeps changing. To tackle this issue, we propose a federated spatial-temporal incremental learning approach, named FedSTIL, which leverages both lifelong learning and federated learning to continuously optimize models deployed on many distributed edge clients. Unlike previous efforts, FedSTIL aims to mine spatial-temporal correlations among the knowledge learnt from different edge clients. Specifically, the edge clients first periodically extract general representations of drifted data to optimize their local models. Then, the learnt knowledge from edge clients will be aggregated by centralized parameter server, where the knowledge will be selectively and attentively distilled from spatial- and temporal-dimension with carefully designed mechanisms. Finally, the distilled informative spatial-temporal knowledge will be sent back to correlated edge clients to further improve the recognition accuracy of each edge client with a lifelong learning method. Extensive experiments on a mixture of five real-world datasets demonstrate that our method outperforms others by nearly 4% in Rank-1 accuracy, while reducing communication cost by 62%. All implementation codes are publicly available on https://github.com/MSNLAB/Federated-Lifelong-Person-ReID.

Lifelong learning with deep conditional generative replay for dynamic and adaptive modeling towards net zero emissions target in building energy system

Deep learning has been advocated as the predominant modeling method in the next-generation green building energy systems for energy prediction, predictive maintenance and control optimization. However, in response to external changes, the limited adaptability to new contents and catastrophic forgetting of previously learnt knowledge result in diminished accuracy and robustness, significantly blocking its practical application. To this end, a novel lifelong learning method with deep generative replay was proposed for dynamic and adaptive modeling to conserve energy and mitigate emissions in building energy systems. The presented lifelong learning method was characterized by the alternate training of the task solver and the replay generator in sequential energy task learning to alleviate the catastrophic forgetting. The replay generator provided the past data for the task solver to retain previous energy knowledge while learn new information, which was a conditional generative model instead of explicitly storing data to save resources and protect privacy. In order to validate its technical feasibility, a field experiment was conducted in a specially constructed net zero energy building for the case study on solar power generation prediction. The overall accuracy of proposed method was 53.4% higher than the standard method through fine-tuning and reached 0.89, which closely approaches the theoretical upper bound of 0.91 obtained by the joint training. Moreover, the proposed method effectively retained previously learnt knowledge in sequential energy task learning, evidenced by an average forgetting rate lower than 0.10. Furthermore, extensive comparative experiments have demonstrated the superiority of the proposed method over other machine learning models based on retraining or incremental training. Our study is expected to develop more flexible and robust deep learning models for improving energy efficiency and promoting the carbon neutrality in building energy systems.

Dynamic Multi-objective Optimization for Coagulating Process of Carbon Fiber Precursor Based on Lifelong Learning

Process parameter optimization is an essential link in the coagulating process of carbon fiber. In this paper, considering the dynamic factors of the coagulating bath environment, a dynamic multi-objective optimization problem (DMOP) model for the coagulating process is constructed with process parameters as decision variables and performance indicators as optimization objectives. We combine lifelong learning (LLL) and multi-objective optimization to solve this model and propose a lifelong learning-based dynamic multi-objective evolutionary algorithm (LLL-DMOEA). In LLL-DMOEA, the lifelong learning method is used to learn common knowledge in historical environments. After the arrival of the new environment, we use the common knowledge to generate a high-quality initial population and speed up the process of the multi-objective optimization algorithm to find the Pareto-optimal set (POS) in the new environment. At the same time, common knowledge only requires information in historical environments. The response time to environmental changes can be sped up by learning before the new environment arrives. Experimental results show that the proposed algorithm can effectively solve the optimization problem of process parameters in the coagulating process.

Toward Lifelong Learning for Industrial Defect Classification: A Proposed Framework

Automatic defect inspection is an important application for the development of smart factories in the era of Industry 4.0. It gathers data from production lines to train a model to automatically recognize certain types of defects. However, the defect types may vary in the production process, and it is difficult for the old model to adapt to new types of defects directly. Considering this problem, we propose an industrial defect classification framework based on lifelong learning, which continuously updates the defect classification model to adapt to different industrial scenarios as new defect appears. Specifically, a novel recursive gradient optimization (RGO) lifelong learning method is used to train the defect classification model, which only needs a fixed network capacity and does not need data replay. The proposed framework is evaluated on an experimental setup of six defect classification tasks. Extensive experiments in real scenarios are performed, demonstrating that the proposed framework can effectively relieve the catastrophic forgetting problem in lifelong learning compared with other state-of-the-art methods.

VLAD: Task-agnostic VAE-based lifelong anomaly detection

Lifelong learning represents an emerging machine learning paradigm that aims at designing new methods providing accurate analyses in complex and dynamic real-world environments. Although a significant amount of research has been conducted in image classification and reinforcement learning, very limited work has been done to solve lifelong anomaly detection problems. In this context, a successful method has to detect anomalies while adapting to changing environments and preserving knowledge to avoid catastrophic forgetting. While state-of-the-art online anomaly detection methods are able to detect anomalies and adapt to a changing environment, they are not designed to preserve past knowledge. On the other hand, while lifelong learning methods are focused on adapting to changing environments and preserving knowledge, they are not tailored for detecting anomalies, and often require task labels or task boundaries which are not available in task-agnostic lifelong anomaly detection scenarios. This paper proposes VLAD, a novel VAE-based Lifelong Anomaly Detection method addressing all these challenges simultaneously in complex task-agnostic scenarios. VLAD leverages the combination of lifelong change point detection and an effective model update strategy supported by experience replay with a hierarchical memory maintained by means of consolidation and summarization. An extensive quantitative evaluation showcases the merit of the proposed method in a variety of applied settings. VLAD outperforms state-of-the-art methods for anomaly detection, presenting increased robustness and performance in complex lifelong settings.

Lifelong learning with Shared and Private Latent Representations learned through synaptic intelligence

This paper explores a novel lifelong learning method with Shared and Private Latent Representations (SPLR), which are learned through synaptic intelligence. To solve a sequence of tasks, by considering the entire parameter learning trajectory, SPLR can learn task-invariant representation which changes little, and task-specific features that change greatly along the entire parameter updating trajectory. Therefore, in the lifelong learning scenarios, our model can obtain a task-invariant structure shared by all tasks and also contain some private properties that are task-specific to each task. To reduce the parameter quantity, a ℓ1 regularization to promote sparsity is employed in the weights. We use multiple datasets under lifelong learning scenes to verify our SPLR, on these datasets it can get comparable performance compared with existing lifelong learning approaches, and learn a sparse network which means fewer parameters while requiring less model training time.

Graph Lifelong Learning: A Survey

Graph learning is a popular approach for perfor ming machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide due to the availability of graph data ranging from all types of networks to information systems. Most graph learning methods assume that the graph is static and its complete structure is known during training. This limits their applicability since they cannot be applied to problems where the underlying graph grows over time and/or new tasks emerge incrementally. Such applications require a lifelong learning approach that can learn the graph continuously and accommodate new information whilst retaining previously learned knowledge. Lifelong learning methods that enable continuous learning in regular domains like images and text cannot be directly applied to continuously evolving graph data, due to its irregular structure. As a result, graph lifelong learning is gaining attention from the research community. This survey paper provides a comprehensive overview of recent advancements in graph lifelong learning, including the categorization of existing methods, and the discussions of potential applications and open research problems.

A Lifelong Learning Method Based on Generative Feature Replay for Bearing Diagnosis With Incremental Fault Types

Deep learning (DL)-based fault diagnosis models need to collect sufficient fault information for each fault type to ensure high-precision diagnosis. Some unexpected and new fault types will inevitably appear in actual conditions, which are called incremental fault types or class increment. Traditional DL models require the costly collection of all known data for retraining; while the use of new fault data may lead to catastrophic forgetting of old tasks. To solve the problem of bearing diagnosis with incremental fault types, a lifelong learning method based on generative feature replay (LLMGFR) is proposed in this study. A feature distillation method is put forward in this method to avoid forgetting in the feature extractor. The generator is trained to produce old task features. The generated features are mixed with real features of the current task to solve the imbalance problem and catastrophic forgetting of the classifier effectively. According to incremental fault diagnosis cases, LLMGFR can learn constantly and adaptively in dynamic environments with incremental fault types.

A Lifelong Learning Method for Gearbox Diagnosis With Incremental Fault Types

Deep learning (DL)-based fault diagnosis models have to collect the most comprehensive data of mechanical fault types to ensure reliability. In real scenarios, due to complex, variable operating conditions, machines often generate unexpected faults that lead to an increment of fault types, causing the diagnosis model to be invalid. Therefore, the data of new fault types are needed to retrain the model. However, DL models suffer from catastrophic forgetting when incrementally learning new classes. To solve the problem of the diagnosis of increasing fault types, a lifelong learning method for fault diagnosis (LLMFD) is proposed in this paper under the lifelong learning paradigm. The key of LLMFD is a proposed dual-branch aggregation networks (DBANets) framework that is combined with reserved exemplars to learn the new fault types without forgetting the old ones. In DBANets, each residual block layer has a dynamic block and a steady block to solve the stability–plasticity dilemma in lifelong learning. The aggregation weights are adopted to balance stability and plasticity. LLMFD is applied to a diagnosis case of incremental fault types. Results verify that LLMFD is superior to other lifelong learning methods and has satisfactory robustness.

COVID-19 as a Catalyst for Digital Lifelong Learning and Reskilling

Due to COVID-19 and following social distancing many face-to-face business as well as educational activities have been replaced by digital ones. Progress towards the Sustainable Development Goal 4 (SDG4) to achieve quality education for all and lifelong learning will stagnate. But the radical changes within education due COVID-19 also open the way for new forms of lifelong learning by using e-learning platforms - digital lifelong learning. This paper is based on literature review as well as work of the author within the Study Group Lifelong Learning and projects. It presents first critical skills required in the next years for reskilling and methods and pedagogies that should be included into education and training. Secondly the necessity and advantages of digital lifelong learning during and after COVID-19 pandemic and how Sustainable Development Goal 4 (SDG 4) will be supported are shortly described. Thirdly how digital lifelong learning methods can be used in entrepreneurship education and some lifelong skills developed within projects worked by the author as well as used methods are discussed. Some conclusions and recommendations are given i.e., entreprene urship educators should be better trained and critical in their methods and educational agencies should foster digital frameworks for entrepreneurship education. Research studies are necessary to know how entrepreneurship educators have embedded digital lifelong learning into their lessons, including positive and negative experiences, and if exists a correlation between a country level of COVID-19, country economic situation, digitalization and digital lifelong learning/entrepreneurship education.

A Deep Lifelong Learning Method for Digital Twin-Driven Defect Recognition With Novel Classes

Abstract Recently, digital twins (DTs) have become a research hotspot in smart manufacturing, and using DTs to assist defect recognition has also become a development trend. Real-time data collection is one of the advantages of DTs, and it can help the realization of real-time defect recognition. However, DT-driven defect recognition cannot be realized unless some bottlenecks of the recognition models, such as the time efficiency, have been solved. To improve the time efficiency, novel defect class recognition is an essential problem. Most of the existing methods can only recognize the known defect classes, which are available during training. For new incoming classes, known as novel classes, these models must be rebuilt, which is time-consuming and costly. This greatly impedes the realization of DT-driven defect recognition. To overcome this problem, this paper proposes a deep lifelong learning method for novel class recognition. The proposed method uses a two-level deep learning architecture to detect and recognize novel classes, and uses a lifelong learning strategy, weight imprinting, to upgrade the model. With these improvements, the proposed method can handle novel classes timely. The experimental results indicate that the proposed method achieves good results for the novel classes, and it has almost no delay for production. Compared with the rebuilt methods, the time cost is reduced by at least 200 times. This result suggests that the proposed method has good potential in the realization of DT-driven defect recognition.

Automatic segmentation of three clinical target volumes in radiotherapy using lifelong learning

Background and purposeConvolutional neural networks (CNNs) have comparable human level performance in automatic segmentation. An important challenge that CNNs face in segmentation is catastrophic forgetting. They lose performance on tasks that were previously learned when trained on task. In this study, we propose a lifelong learning method to learn multiple segmentation tasks continuously without forgetting previous tasks. Materials and methodsThe cohort included three tumors, 800 patients of which had nasopharyngeal cancer (NPC), 800 patients had breast cancer, and 800 patients had rectal cancer. The tasks included segmentation of the clinical target volume (CTV) of these three cancers. The proposed lifelong learning network adopted dilation adapter to learn three segmentation tasks one by one. Only the newly added dilation adapter (seven layers) was fine tuning for incoming new task, whereas all the other learned layers were frozen. ResultsCompared with single-task, multi-task or transfer learning, the proposed lifelong learning can achieve better or comparable segmentation accuracy with a DSC of 0.86 for NPC, 0.89 for breast cancer, and 0.87 for rectal cancer. Lifelong learning can avoid forgetting in sequential learning and yield good performance with less training data. Furthermore, it is more efficient than single-task or transfer learning, which reduced the number of parameters, size of model, and training time by ~58.8%, ~55.6%, and ~25.0%, respectively. ConclusionThe proposed method preserved the knowledge of previous tasks while learning a new one using a dilation adapter. It could yield comparable performance with much less training data, model parameters, and training time.

L3DOC: Lifelong 3D Object Classification.

3D object classification has been widely applied in both academic and industrial scenarios. However, most state-of-the-art algorithms rely on a fixed object classification task set, which cannot tackle the scenario when a new 3D object classification task is coming. Meanwhile, the existing lifelong learning models can easily destroy the learned tasks performance, due to the unordered, large-scale, and irregular 3D geometry data. To address these challenges, we propose a Lifelong 3D Object Classification (i.e., L3DOC) model, which can consecutively learn new 3D object classification tasks via imitating "human learning". More specifically, the core idea of our model is to capture and store the cross-task common knowledge of 3D geometry data in a 3D neural network, named as point-knowledge, through employing layer-wise point-knowledge factorization architecture. Afterwards, a task-relevant knowledge distillation mechanism is employed to connect the current task to previous relevant tasks and effectively prevent catastrophic forgetting. It consists of a point-knowledge distillation module and a transforming-space distillation module, which transfers the accumulated point-knowledge from previous tasks and soft-transfers the compact factorized representations of the transforming-space, respectively. To our best knowledge, the proposed L3DOC algorithm is the first attempt to perform deep learning on 3D object classification tasks in a lifelong learning way. Extensive experiments on several point cloud benchmarks illustrate the superiority of our L3DOC model over the state-of-the-art lifelong learning methods.

Quality-Aware Neural Adaptive Video Streaming With Lifelong Imitation Learning

Existing Adaptive Bitrate (ABR) algorithms pick future video chunks' bitrates via fixed rules or offline trained models to ensure good quality of experience (QoE) for Internet video. Nevertheless, data analysis demonstrates that a good ABR algorithm is required to continually and fast update for adapting itself to time-varying network conditions. Therefore, we propose Comyco, a video quality-aware learning-based ABR approach that enormously improves recent schemes by i) picking the chunk with higher perceptual video qualities rather than video bitrates; ii) training the policy via imitating expert trajectories given by the expert strategy; iii) employing the lifelong learning method to continually train the model w.r.t the fresh trace collected by the users. To achieve this, we develop a complete quality-aware lifelong imitation learning-based ABR system, construct quality-based neural network architecture, collect a quality-driven video dataset, and estimate QoE metrics with video quality features. Using trace-driven and real-world experiments, we demonstrate Comyco reaches 1700-fold improvements in the number of samples required and 16-fold speedup in the training time compared with the prior work. Meanwhile, Comyco outperforms existing methods, with the improvements on average QoE of 7.5%-16.79%. Moreover, experimental results on continual training also illustrate that lifelong learning helps Comyco further improve the average QoE of 1.07%-9.81% in comparison to the offline trained model.

Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task.

Guided Policy Search for Sequential Multitask Learning

Policy search in reinforcement learning (RL) is a practical approach to interact directly with environments in parameter spaces, that often deal with dilemmas of local optima and real-time sample collection. A promising algorithm, known as guided policy search (GPS), is capable of handling the challenge of training samples using trajectory-centric methods. It can also provide asymptotic local convergence guarantees. However, in its current form, the GPS algorithm cannot operate in sequential multitask learning scenarios. This is due to its batch-style training requirement, where all training samples are collectively provided at the start of the learning process. The algorithm’s adaptation is thus hindered for real-time applications, where training samples or tasks can arrive randomly. In this paper, the GPS approach is reformulated, by adapting a recently proposed, lifelong-learning method, and elastic weight consolidation. Specifically, Fisher information is incorporated to impart knowledge from previously learned tasks. The proposed algorithm, termed sequential multitask learning-GPS, is able to operate in sequential multitask learning settings and ensuring continuous policy learning, without catastrophic forgetting. Pendulum and robotic manipulation experiments demonstrate the new algorithms efficacy to learn control policies for handling sequentially arriving training samples, delivering comparable performance to the traditional, and batch-based GPS algorithm. In conclusion, the proposed algorithm is posited as a new benchmark for the real-time RL and robotics research community.

Peer Coaching in a Research-Based Teachers’ Professional Learning Method for Lifelong Learning: A Perspective

Teacher professional development (PD) has been claimed to be the foundation for transforming school culture. Any PD activity with a human infrastructure that is composed of teachers, researchers, and policy makers who together form a professional learning community (PLC) situated in a local school must incorporate the team’s appreciation of collective efficacy and sense of community in the learning environment. A PLC must exemplify the concept of ongoing collaborative experiential learning through experimentation and reflection on emerging practices. It is expected, therefore, that with everyone's active involvement in the support structure, teachers' PD will be positively impacted and reflected in approaches to professional development. Fundamental to the adult learning environment is the process of collaborative inquiry where participants critically reflect on their own experiences. The process of collaborative inquiry encapsulates the notion that as teachers are regarded as lifelong learners, they need to gather insights from their experiences with the support of their colleagues to ensure that their learning process contributes to the enhancement of the quality of teaching and learning outcomes. Collaborative inquiry captures the idea of co-learning PD where professional knowledge and skills are acquired and sustained in an authentic teaching environment that aims to foster sustainable changes in teaching practices. Grounded in the principles of adult learning, this article presents a methodological perspective on how educational institutions can form a professional learning community within the school context where problems from past experiences are critically examined and serve as a foundation to professionally reflect, think, and act. Il a été affirmé que le développement professionnel des enseignants est la base de la transformation de la culture scolaire. Toute activité liée au développement professionnel ayant une infrastructure humaine composée d’enseignants, de chercheurs et de décideurs qui forment une communauté d’apprentissage professionnelle (CAP) dans une école locale doit incorporer l’appréciation de l’équipe pour l’efficacité collective et le sentiment de communauté dans le milieu d’apprentissage. Une CAP doit illustrer, par l’expérimentation et la réflexion sur les pratiques émergentes, le concept de l’apprentissage expérientiel collaboratif et continu. On s’attend alors que l’implication active de tout le monde dans la structure de soutien aura un impact positif sur le développement professionnel des enseignants et sur les approches à ce cheminement. Le processus d’enquête collaborative où les participants se livrent à une réflexion critique sur leurs propres expériences constitue un élément fondamental du milieu de l’éducation des adultes. L’enquête en collaboration résume la notion qu’en tant qu’apprenants à vie, les enseignants se doivent de recueillir des connaissances de leurs expériences avec l’appui de leurs collègues et pour s’assurer que leur cheminement contribue à l’amélioration de la qualité de l’enseignement et des résultats d’apprentissage. L’enquête collaborative englobe l’idée du co-apprentissage dans le contexte du développement professionnel au cours duquel des connaissances et des habiletés professionnelles sont acquises et maintenues dans un milieu pédagogique authentique qui vise la promotion de changements durables dans la pratique enseignante. Fondée sur les principes de la formation des adultes, cet article présente une perspective méthodologique sur la formation, par les établissements d’enseignement, d’une communauté d’apprentissage professionnelle dans un milieu scolaire où les expériences du passé font l’objet d’un examen critique et servent de base à des réflexions et des actions professionnelles. Mots clés : développement professionnel, formation en cours d’emploi, perfectionnement professionnel, collaboration

Peer Coaching in a Research-Based Teachers’ Professional Learning Method for Lifelong Learning: A Perspective

Teacher professional development (PD) has been claimed to be the foundation for transforming school culture. Any PD activity with a human infrastructure that is composed of teachers, researchers, and policy makers who together form a professional learning community (PLC) situated in a local school must incorporate the team’s appreciation of collective efficacy and sense of community in the learning environment. A PLC must exemplify the concept of ongoing collaborative experiential learning through experimentation and reflection on emerging practices. It is expected, therefore, that with everyone's active involvement in the support structure, teachers' PD will be positively impacted and reflected in approaches to professional development. Fundamental to the adult learning environment is the process of collaborative inquiry where participants critically reflect on their own experiences. The process of collaborative inquiry encapsulates the notion that as teachers are regarded as lifelong learners, they need to gather insights from their experiences with the support of their colleagues to ensure that their learning process contributes to the enhancement of the quality of teaching and learning outcomes. Collaborative inquiry captures the idea of co-learning PD where professional knowledge and skills are acquired and sustained in an authentic teaching environment that aims to foster sustainable changes in teaching practices. Grounded in the principles of adult learning, this article presents a methodological perspective on how educational institutions can form a professional learning community within the school context where problems from past experiences are critically examined and serve as a foundation to professionally reflect, think, and act.Il a ete affirme que le developpement professionnel des enseignants est la base de la transformation de la culture scolaire. Toute activite liee au developpement professionnel ayant une infrastructure humaine composee d’enseignants, de chercheurs et de decideurs qui forment une communaute d’apprentissage professionnelle (CAP) dans une ecole locale doit incorporer l’appreciation de l’equipe pour l’efficacite collective et le sentiment de communaute dans le milieu d’apprentissage. Une CAP doit illustrer, par l’experimentation et la reflexion sur les pratiques emergentes, le concept de l’apprentissage experientiel collaboratif et continu. On s’attend alors que l’implication active de tout le monde dans la structure de soutien aura un impact positif sur le developpement professionnel des enseignants et sur les approches a ce cheminement.Le processus d’enquete collaborative ou les participants se livrent a une reflexion critique sur leurs propres experiences constitue un element fondamental du milieu de l’education des adultes. L’enquete en collaboration resume la notion qu’en tant qu’apprenants a vie, les enseignants se doivent de recueillir des connaissances de leurs experiences avec l’appui de leurs collegues et pour s’assurer que leur cheminement contribue a l’amelioration de la qualite de l’enseignement et des resultats d’apprentissage. L’enquete collaborative englobe l’idee du co-apprentissage dans le contexte du developpement professionnel au cours duquel des connaissances et des habiletes professionnelles sont acquises et maintenues dans un milieu pedagogique authentique qui vise la promotion de changements durables dans la pratique enseignante. Fondee sur les principes de la formation des adultes, cet article presente une perspective methodologique sur la formation, par les etablissements d’enseignement, d’une communaute d’apprentissage professionnelle dans un milieu scolaire ou les experiences du passe font l’objet d’un examen critique et servent de base a des reflexions et des actions professionnelles.Mots cles : developpement professionnel, formation en cours d’emploi, perfectionnement professionnel, collaboration