Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Existing FCIL methods call for high communication costs and exemplars from previous classes. We propose a novel rehearsal-free method for FCIL named prototypes-injected prompt (PIP) that involves 3 main ideas: a) prototype injection on prompt learning, b) prototype augmentation, and c) weighted Gaussian aggregation on the server side. Our experiment result shows that the proposed method outperforms the current state of the arts (SOTAs) with a significant improvement (up to 33%) in CIFAR100, MiniImageNet, and TinyImageNet datasets. Our extensive analysis demonstrates the robustness of PIP in different task sizes, and the advantage of requiring smaller participating local clients, and smaller global rounds. For further study, source codes of PIP, baseline, and experimental logs are shared publicly in https://github.com/anwarmaxsum/PIP.

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks efficiently, while avoiding catastrophic forgetting. Existing methods primarily focus on single domains, restricting their applicability to specific problems. In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains. Our method combines inter- and intra-task cross-attention mechanisms within a compact convolutional network. This integration enables the model to maintain alignment with features from previous tasks, thereby delaying the data drift that may occur between tasks, while performing unsupervised cross-domain (UDA) between related domains. By leveraging an intra-task-specific pseudo-labeling method, we ensure accurate input pairs for both labeled and unlabeled samples, enhancing the learning process. To validate our approach, we conduct extensive experiments on public UDA datasets, showcasing its positive performance on cross-domain continual learning challenges. Additionally, our work introduces incremental ideas that contribute to the advancement of this field. We make our code and models available to encourage further exploration and reproduction of our results: https://github.com/IvsucramlCDCL

Few-Shot Class-Incremental Learning (FSCIL)presents an extension of the Class Incremental Learning (CIL)problem where a model is faced with the problem of data scarcity while addressing the Catastrophic Forgetting (CF)problem. This problem remains an open problem because all recent works are built upon the Convolutional Neural Networks (CNNs)performing sub-optimally compared to the transformer approaches. Our paper presents Robust Transformer Approach (ROBUSTA)built upon the Compact Convolutional Transformer (CCT). The issue of overfitting due to few samples is overcome with the notion of the stochastic classifier, where the classifier's weights are sampled from a distribution with mean and variance vectors, thus increasing the likelihood of correct classifications, and the batch-norm layer to stabilize the training process. The issue of CFis dealt with the idea of delta parameters, small task-specific trainable parameters while keeping the backbone networks frozen. A non-parametric approach is developed to infer the delta parameters for the model's predictions. The prototype rectification approach is applied to avoid biased prototype calculations due to the issue of data scarcity. The advantage of ROBUSTAis demonstrated through a series of experiments in the benchmark problems where it is capable of outperforming prior arts with big margins without any data augmentation protocols.

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite numerous efforts to mitigate CF, it remains the significant challenge particularly in complex changing environments. This challenge is even more pronounced in cross-domain adaptation following the continual learning (CL) setting, which is a more challenging and realistic scenario that is under-explored. To this end, this article proposes a cross-domain CL approach making possible to deploy a single model in such environments without additional labelling costs. Our approach, namely continual learning approach for many processes (CLAMP), integrates a class-aware adversarial domain adaptation strategy to align a source domain and a target domain. An assessor-guided learning process is put forward to navigate the learning process of a base model assigning a set of weights to every sample controlling the influence of every sample and the interactions of each loss function in such a way to balance the stability and plasticity dilemma thus preventing the CF problem. The first assessor focuses on the negative transfer problem rejecting irrelevant samples of the source domain while the second assessor prevents noisy pseudo labels of the target domain. Both assessors are trained in the meta-learning approach using random transformation techniques and similar samples of the source domain. Theoretical analysis and extensive numerical validations demonstrate that CLAMP significantly outperforms established baseline algorithms across all experiments by at least 10% margin.

This paper proposes an assessor-guided learning strategy for continual learning where an assessor guides the learning process of a base learner by controlling the direction and pace of the learning process thus allowing an efficient learning of new environments while protecting against the catastrophic interference problem. The assessor is trained in a meta-learning manner with a meta-objective to boost the learning process of the base learner. It performs a soft-weighting mechanism of every sample accepting positive samples while rejecting negative samples. The training objective of a base learner is to minimize a meta-weighted combination of the cross entropy loss function, the dark experience replay (DER) loss function and the knowledge distillation loss function whose interactions are controlled in such a way to attain an improved performance. A compensated over-sampling (COS) strategy is developed to overcome the class imbalanced problem of the episodic memory due to limited memory budgets. Our approach, Assessor-Guided Learning Approach (AGLA), has been evaluated in the class-incremental and task-incremental learning problems. AGLA achieves improved performances compared to its competitors while the theoretical analysis of the COS strategy is offered. Source codes of AGLA, baseline algorithms and experimental logs are shared publicly in https://github.com/anwarmaxsum/AGLA for further study.

Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in domains related to node and graph classification/regression tasks, they mostly deal with a single task. Continual learning on graphs is largely unexplored and existing graph continual learning approaches are limited to the task-incremental learning scenarios. This paper proposes a graph continual learning strategy that combines the architecture-based and memory-based approaches. The structural learning strategy is driven by reinforcement learning, where a controller network is trained in such a way to determine an optimal number of nodes to be added/pruned from the base network when new tasks are observed, thus assuring sufficient network capacities. The parameter learning strategy is underpinned by the concept of Dark Experience replay method to cope with the catastrophic forgetting problem. Our approach is numerically validated with several graph continual learning benchmark problems in both task-incremental learning and class-incremental learning settings. Compared to recently published works, our approach demonstrates improved performance in both the settings. The implementation code can be found at https://github.com/codexhammer/gcl.

Designing a Convolutional Neural Networks (CNN) is a complex task and requires expert knowledge to optimize the performance and network architecture. In this paper, a novel data-driven approach is proposed to determine the architecture of CNN models. The proposed Autonomous Convolutional Neural Networks (AutoCNNThe executable code and original numerical results can be downloaded from (https://tinyurl.com/AutoCNN)) algorithm introduces data driven strategies for addition of new convolutional layers, pruning of redundant filters and training cycle optimization. AutoCNN is evaluated using MNIST, MNIST-rot-back-image, Fashion MNIST and the ADHD200 datasets to measure the performance on small datasets with varied feature distributions. The results indicate that AutoCNN optimizes the CNN network architecture and helps maximise the classification performance. The data-driven network determination approach introduced in this paper was found to not only provides competitive performance similar to existing evolutionary computation based network determination algorithms in literature, but was found to be an effective optimization tool to improve the performance of existing CNN architectures. Further, the AutoCNN was found to highly immune to noise in the dataset and has proven to be effective method to transfer knowledge between related datasets. Therefore, the AutoCNN is a highly versatile CNN architecture determination tool that has a wide range of applications in the field of autonomous driving, medical image analysis, image enhancement, camera based security monitoring and image based fault detection

The existing methods to calculate the Eigenvector Centrality(EC) tend to not be robust enough for determination of EC in low time complexity or not well-scalable for large networks, hence rendering them practically unreliable/ computationally expensive. So, it is of the essence to develop a method that is scalable in low computational time. Hence, we propose a deep learning model for the identification of nodes with high Eigenvector Centrality. There have been a few previous works in identifying the high ranked nodes with supervised learning methods, but in real-world cases, the graphs are not labelled and hence deployment of supervised learning methods becomes a hazard and its usage becomes impractical. So, we devise CUL(Centrality with Unsupervised Learning) method to learn the relative EC scores in a network in an unsupervised manner. To achieve this, we develop an Encoder-Decoder based framework that maps the nodes to their respective estimated EC scores. Extensive experiments were conducted on different synthetic and real-world networks. We compared CUL against a baseline supervised method for EC estimation similar to some of the past works. It was observed that even with training on a minuscule number of training datasets, CUL delivers a relatively better accuracy score when identifying the higher ranked nodes than its supervised counterpart. We also show that CUL is much faster and has a smaller runtime than the conventional baseline method for EC computation. The code is available at https://github.com/codexhammer/CUL.

Evolving fuzzy systems (EFS) have received increased attention from the community for the purpose of data stream modeling in an incremental, single-pass and transparent manner. To date, a wide variety of EFS approaches have been developed and successfully used in real-world applications which address structural evolution and parameter adaptation in single EFS models. We propose a specific ensemble scheme of EFS to increase their robustness in predictive performance on new stream samples. Our approach relies on an online variant of bagging in which various EFS ensemble members are generated from online bags, that is, the members are updated based on a specific probabilistic online sampling technique, and this with guaranteed convergence to classical sampling in batch bagging. The autonomous pruning of ensemble members is undertaken to omit undesired members with atypically higher errors than other members. We propose two variants, hard pruning where undesired members are deleted forever from the ensemble, and soft pruning where members receive weights to calculate the overall ensemble prediction, according to their single performance; thus, members who are undesired at a certain point of time may be dynamically recalled at a later stage. The autonomous evolution of new ensemble members is carried out whenever a drift in the stream is detected, based on a significantly worsening performance indicator, measured in terms of the Hoeffding inequality. Newer members typically represent the drifted state better and are thus up-weighed compared to older members within an advanced (weighted) calculation of the overall ensemble prediction. The new approach termed online bagged EFS (OB-EFS) was successfully evaluated and compared with single EFS models and related SoA approaches on four data streams from real-world applications (containing various noise levels, drifts and new operating conditions) and showed significantly lower prediction error trend lines.

With the increasing demand of product supply, manufacturers are in urgent need of online tool condition monitoring (TCM) without compromising with the maintenance cost in terms of time as well as man-power requirement. However, the existing machine learning models for TCM are mostly offline and not suitable for the non-stationary environment of the machining settings. Moreover, the access of the ground truth always imposes a shutdown of the machining process and the existing models are severely affected by such delay in receiving labelled samples. In order to tackle these issues, we propose SERMON as a novel learning model based on a pair of self-evolving mutually-operative recurrent neural networks. The proposed SERMON is well-equipped with features for automated and real-time monitoring of machine fault status even in the finite/infinite label delay scenario. The experimental evaluation of SERMON using real-world dataset on 3D-printing process demonstrates its effectiveness in online fault detection under non-stationary as well as delayed label context of the machining process. Additional comparative study on large-scale benchmark streaming datasets further exhibits the scalability power of SERMON.

The feasibility of existing data stream algorithms is often hindered by the weakly supervised condition of data streams. A self-evolving deep neural network, namely Parsimonious Network (ParsNet), is proposed as a solution to various weakly-supervised data stream problems. A self-labelling strategy with hedge (SLASH) is proposed in which its auto-correction mechanism copes with the accumulation of mistakes significantly affecting the model's generalization. ParsNet is developed from a closed-loop configuration of the self-evolving generative and discriminative training processes exploiting shared parameters in which its structure flexibly grows and shrinks to overcome the issue of concept drift with/without labels. The numerical evaluation has been performed under two challenging problems, namely sporadic access to ground truth and infinitely delayed access to the ground truth. Our numerical study shows the advantage of ParsNet with a substantial margin from its counterparts in the high-dimensional data streams and infinite delay simulation protocol. To support the reproducible research initiative, the source code of ParsNet along with supplementary materials are made available at https://bit.ly/2qNW7p4.

Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain, different period of drifts in the source and target domains. Autonomous transfer learning (ATL) is proposed in this paper as a flexible deep learning approach for the online unsupervised transfer learning problem across many streaming processes. ATL offers an online domain adaptation strategy via the generative and discriminative phases coupled with the KL divergence based optimization strategy to produce a domain invariant network while putting forward an elastic network structure. It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain. Rigorous numerical evaluation has been conducted along with comparison against recently published works. ATL demonstrates improved performance while showing significantly faster training speed than its counterparts.

Autonomous construction of deep neural network (DNNs) is desired for data streams because it potentially offers two advantages: proper model's capacity and quick reaction to drift and shift. While self-organizing mechanism of DNNs remains an open issue, this task is even more challenging to be developed for standard multi-layer DNNs than that using the different-depth structures, because addition of a new layer results in information loss of previously trained knowledge. A Neural Network with Dynamically Evolved Capacity (NADINE) is proposed in this paper. NADINE features a fully open structure where its network structure, depth and width, can be automatically evolved from scratch in the online manner and without the use of problem-specific thresholds. NADINE is structured under a standard MLP architecture and the catastrophic forgetting issue during the hidden layer addition phase is resolved using the proposal of soft-forgetting and adaptive memory methods. The advantage of NADINE, namely elastic structure and online learning trait, is numerically validated using nine data stream classification and regression problems where it demonstrates performance's improvement over prominent algorithms in all problems. In addition, it is capable of dealing with data stream regression and classification problems equally well.

In this paper, we propose MUSE-RNN, a multilayer self-evolving recurrent neural network model for real-time classification of streaming data. Unlike the existing approaches, MUSE-RNN offers special treatment towards capturing temporal aspects of data stream through its novel recurrent learning approach based on the teacher forcing policy. Novelties here are twofold. First, in contrast to the traditional RNN models, MUSE-RNN has intrinsic ability to self-adjust its capacity by growing and pruning hidden nodes as well as layers, to handle the ever-changing characteristics of data stream. Second, MUSERNN adopts a unique scoring-based layer adaptation mechanism, which makes it capable of recalling prior tasks, with minimum exploitation of network parameters. The performance of MUSERNN is evaluated in comparison with a number of state-of-theart techniques, using seven popular data streams and continual learning problems under prequential test-then-train protocol. Experimental results demonstrate the effectiveness of MUSERNN in stream classification scenario.

The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely autonomous deep learning (ADL), is proposed in this paper. Unlike traditional deep learning methods, ADL features a flexible structure where its network structure can be constructed from scratch with the absence of initial network structure via the self-constructing network structure. ADL specifically addresses catastrophic forgetting by having a different-depth structure which is capable of achieving a trade-off between plasticity and stability. Network significance (NS) formula is proposed to drive the hidden nodes growing and pruning mechanism. Drift detection scenario (DDS) is put forward to signal distributional changes in data streams which induce the creation of a new hidden layer. Maximum information compression index (MICI) method plays an important role as a complexity reduction module eliminating redundant layers. The efficacy of ADL is numerically validated under the prequential test-then-train procedure in lifelong environments using nine popular data stream problems. The numerical results demonstrate that ADL consistently outperforms recent continual learning methods while characterizing the automatic construction of network structures.