Knowledge transfer in lifelong machine learning: a systematic literature review.

Lifelong Machine Learning (LML) denotes a scenario involving multiple sequential tasks, each accompanied by its respective dataset, in order to solve specific learning problems. In this context, the focus of LML techniques is on utilizing already acquired knowledge to adapt to new tasks efficiently. Essentially, LML concerns about facing new tasks while exploiting the knowledge previously gathered from earlier tasks not only to help in adapting to new tasks but also to enrich the understanding of past ones. By understanding this concept, one can better grasp one of the major obstacles in LML, known as Knowledge Transfer (KT). This systematic literature review aims to explore state-of-the-art KT techniques within LML and assess the evaluation metrics and commonly utilized datasets in this field, thereby keeping the LML research community updated with the latest developments. From an initial pool of 417 articles from four distinguished databases, 30 were deemed highly pertinent for the information extraction phase. The analysis recognizes four primary KT techniques: Replay, Regularization, Parameter Isolation, and Hybrid. This study delves into the characteristics of these techniques across both neural network (NN) and non-neural network (non-NN) frameworks, highlighting their distinct advantages that have captured researchers' interest. It was found that the majority of the studies focused on supervised learning within an NN modelling framework, particularly employing Parameter Isolation and Hybrid for KT. The paper concludes by pinpointing research opportunities, including investigating non-NN models for Replay and exploring applications outside of computer vision (CV).

Lifelong Text-Audio Sentiment Analysis learning.

Sentiment analysis refers to the mining of textual context, which is conducted with the aim of identifying and extracting subjective opinions in textual materials. However, most existing methods neglect other important modalities, e.g., the audio modality, which can provide intrinsic complementary knowledge for sentiment analysis. Furthermore, much work on sentiment analysis cannot continuously learn new sentiment analysis tasks or discover potential correlations among distinct modalities. To address these concerns, we propose a novel Lifelong Text-Audio Sentiment Analysis (LTASA) model to continuously learn text-audio sentiment analysis tasks, which effectively explores intrinsic semantic relationships from both intra-modality and inter-modality perspectives. More specifically, a modality-specific knowledge dictionary is developed for each modality to obtain shared intra-modality representations among various text-audio sentiment analysis tasks. Additionally, based on information dependence between text and audio knowledge dictionaries, a complementarity-aware subspace is developed to capture the latent nonlinear inter-modality complementary knowledge. To sequentially learn text-audio sentiment analysis tasks, a new online multi-task optimization pipeline is designed. Finally, we verify our model on three common datasets to show its superiority. Compared with some baseline representative methods, the capability of the LTASA model is significantly boosted in terms of five measurement indicators.

A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning.

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten. However, comparison of individual methods is nevertheless performed in isolation from the real world by monitoring accumulated benchmark test set performance. The closed world assumption remains predominant, i.e. models are evaluated on data that is guaranteed to originate from the same distribution as used for training. This poses a massive challenge as neural networks are well known to provide overconfident false predictions on unknown and corrupted instances. In this work we critically survey the literature and argue that notable lessons from open set recognition, identifying unknown examples outside of the observed set, and the adjacent field of active learning, querying data to maximize the expected performance gain, are frequently overlooked in the deep learning era. Hence, we propose a consolidated view to bridge continual learning, active learning and open set recognition in deep neural networks. Finally, the established synergies are supported empirically, showing joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, while exhibiting robust open world application.

A novel lifelong machine learning-based method to eliminate calibration drift in clinical prediction models.

OBJECTIVE: Clinical prediction models (CPMs) constructed based on artificial intelligence have been proven to have positive impacts on clinical activities. However, the deterioration of CPM performance over time has rarely been studied. This paper proposes a model updating method to solve the calibration drift issue caused by data drift. MATERIALS AND METHODS: This paper proposes a novel model updating method based on lifelong machine learning (LML). The effectiveness of the proposed method is verified in four tumor datasets, and a comprehensive comparison with other model updating methods is performed. RESULTS: Changes in data distributions cause model performances to drift. The four compared model updating methods have different effects in terms of improving the discrimination and calibration abilities of the tested models. The LML method proposed in this study improves model performance better than or equivalent to the other methods. The proposed method achieved a mean AUC of 0.8249, 0.8780, 0.8261, and 0.8489, a mean AUPRC of 0.7782, 0.9730, 0.4655, and 0.5728, a mean F1 of 0.6866, 0.9552, 0.2985, and 0.3585, and a mean estimated calibration index (ECI) of 0.0320, 0.0338, 0.0101, and 0.0115 using colorectal, lung, breast and prostate cancer datasets. DISCUSSION: The LML framework simultaneously monitors model performance and the distribution of disease risk characteristics, enabling it to effectively address the performance degradation caused by gradual and sudden data drifts and provide reasonable explanations for the causes of performance degradation. CONCLUSION: Monitoring model performance and the underlying data distribution can promote model life cycle iteration with "development-deployment-maintenance-monitoring" as the core, which, in turn, ensures that the model can provide accurate predictions, guides the model update process and explains the causes of model performance changes.