Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic forgetting of old tasks in gradient-based optimization. However, the normalization layers provide an exception, as they are updated interdependently by the gradient and statistics of currently observed training samples, which require specialized strategies to mitigate recency bias. In this work, we focus on the most popular Batch Normalization (BN) and provide an in-depth theoretical analysis of its sub-optimality in continual learning. Our analysis demonstrates the dilemma between balance and adaptation of BN statistics for incremental tasks, which potentially affects training stability and generalization. Targeting on these particular challenges, we propose Adaptive Balance of BN (AdaB$^2$N), which incorporates appropriately a Bayesian-based strategy to adapt task-wise contributions and a modified momentum to balance BN statistics, corresponding to the training and testing stages. By implementing BN in a continual learning fashion, our approach achieves significant performance gains across a wide range of benchmarks, particularly for the challenging yet realistic online scenarios (e.g., up to 7.68%, 6.86% and 4.26% on Split CIFAR-10, Split CIFAR-100 and Split Mini-ImageNet, respectively). Our code is available at https://github.com/lvyilin/AdaB2N.
Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited research conducted in the context of incremental learning where knowledge is introduced sequentially. In this study, we investigate Adversarially Robust Class Incremental Learning (ARCIL), which deals with adversarial robustness in incremental learning. We first explore a series of baselines that integrate incremental learning with existing adversarial training methods, finding that they lead to conflicts between acquiring new knowledge and retaining past knowledge. Furthermore, we discover that training new knowledge causes the disappearance of a key characteristic in robust models: a flat loss landscape in input space. To address such issues, we propose a novel and robust baseline for ARCIL, named \textbf{FL}atness-preserving \textbf{A}dversarial \textbf{I}ncremental learning for \textbf{R}obustness (\textbf{FLAIR}). Experimental results demonstrate that FLAIR significantly outperforms other baselines. To the best of our knowledge, we are the first to comprehensively investigate the baselines, challenges, and solutions for ARCIL, which we believe represents a significant advance toward achieving real-world robustness. Codes are available at \url{https://github.com/HongsinLee/FLAIR}.
Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or experiences. This phenomenon occurs because the network adjusts its weights and connections to minimize the loss on the new task, which can inadvertently overwrite or disrupt the representations that were crucial for the previous tasks. As a result, the the performance of the network on earlier tasks deteriorates, limiting its ability to learn and adapt to a sequence of tasks. In this paper, we propose a novel method for preventing catastrophic forgetting in machine learning applications, specifically focusing on neural networks. Our approach aims to preserve the knowledge of the network across multiple tasks while still allowing it to learn new information effectively. We demonstrate the effectiveness of our method by conducting experiments on various benchmark datasets, including Split MNIST, Split CIFAR10, Split Fashion MNIST, and Split CIFAR100. These datasets are created by dividing the original datasets into separate, non overlapping tasks, simulating a continual learning scenario where the model needs to learn multiple tasks sequentially without forgetting the previous ones. Our proposed method tackles the catastrophic forgetting problem by incorporating negotiated representations into the learning process, which allows the model to maintain a balance between retaining past experiences and adapting to new tasks. By evaluating our method on these challenging datasets, we aim to showcase its potential for addressing catastrophic forgetting and improving the performance of neural networks in continual learning settings.
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical to designing intelligent systems. Many approaches to continual learning rely on stochastic gradient descent and its variants that employ global error updates, and hence need to adopt strategies such as memory buffers or replay to circumvent its stability, greed, and short-term memory limitations. To address this limitation, we have developed a biologically inspired lightweight neural network architecture that incorporates synaptic plasticity mechanisms and neuromodulation and hence learns through local error signals to enable online continual learning without stochastic gradient descent. Our approach leads to superior online continual learning performance on Split-MNIST, Split-CIFAR-10, and Split-CIFAR-100 datasets compared to other memory-constrained learning approaches and matches that of the state-of-the-art memory-intensive replay-based approaches. We further demonstrate the effectiveness of our approach by integrating key design concepts into other backpropagation-based continual learning algorithms, significantly improving their accuracy. Our results provide compelling evidence for the importance of incorporating biological principles into machine learning models and offer insights into how we can leverage them to design more efficient and robust systems for online continual learning.
Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes incrementally. This is due to their inclination to forget the knowledge acquired from previously seen data, a phenomenon termed catastrophic-forgetting. On the other hand, Self-Organizing Maps (SOMs) can model the input space utilizing constrained k-means and thus maintain past knowledge. Here, we propose a novel algorithm inspired by biological neurons, termed Dendritic-Self-Organizing Map (DendSOM). DendSOM consists of a single layer of SOMs, which extract patterns from specific regions of the input space accompanied by a set of hit matrices, one per SOM, which estimate the association between units and labels. The best-matching unit of an input pattern is selected using the maximum cosine similarity rule, while the point-wise mutual information is employed for class inference. DendSOM performs unsupervised feature extraction as it does not use labels for targeted updating of the weights. It outperforms classical SOMs and several state-of-the-art continual learning algorithms on benchmark datasets, such as the Split-MNIST and Split-CIFAR-10. We propose that the incorporation of neuronal properties in SOMs may help remedy catastrophic forgetting.
One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systematically investigate settings where the model sequentially observes samples generated by a series of tasks. In this work, we take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle that facilitates a trade-off between learning and forgetting. We discuss this principle from a Bayesian perspective and show its connections to previous approaches to CL. Based on this principle, we propose a neural network layer, called the Mixture-of-Variational-Experts layer, that alleviates forgetting by creating a set of information processing paths through the network which is governed by a gating policy. Due to the general formulation based on generic utility functions, we can apply this optimality principle to a large variety of learning problems, including supervised learning, reinforcement learning, and generative modeling. We demonstrate the competitive performance of our method in continual supervised learning and in continual reinforcement learning.
Learning from data sequentially arriving, possibly in a non i.i.d. way, with changing task distribution over time is called continual learning. Much of the work thus far in continual learning focuses on supervised learning and some recent works on unsupervised learning. In many domains, each task contains a mix of labelled (typically very few) and unlabelled (typically plenty) training examples, which necessitates a semi-supervised learning approach. To address this in a continual learning setting, we propose a framework for semi-supervised continual learning called Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL). Our framework has a hypernetwork that learns the meta-distribution that generates the weights of a semi-supervised auxiliary classifier generative adversarial network $(\textit{Semi-ACGAN})$ as the base network. We consolidate the knowledge of sequential tasks in the hypernetwork, and the base network learns the semi-supervised learning task. Further, we present $\textit{Semi-Split CIFAR-10}$, a new benchmark for continual semi-supervised learning, obtained by modifying the $\textit{Split CIFAR-10}$ dataset, in which the tasks with labelled and unlabelled data arrive sequentially. Our proposed model yields significant improvements in the continual semi-supervised learning setting. We compare the performance of several existing continual learning approaches on the proposed continual semi-supervised learning benchmark of the Semi-Split CIFAR-10 dataset.
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn in non-stationary distributions. In most settings of the current approaches, the agent starts from randomly initialized parameters and is optimized to master the current task regardless of the usefulness of the learned representation for future tasks. Moreover, each of the future tasks uses all the previously learned knowledge although parts of this knowledge might not be helpful for its learning. These cause interference among tasks, especially when the data of previous tasks is not accessible. In this paper, we propose a new method, named Self-Attention Meta-Learner (SAM), which learns a prior knowledge for continual learning that permits learning a sequence of tasks, while avoiding catastrophic forgetting. SAM incorporates an attention mechanism that learns to select the particular relevant representation for each future task. Each task builds a specific representation branch on top of the selected knowledge, avoiding the interference between tasks. We evaluate the proposed method on the Split CIFAR-10/100 and Split MNIST benchmarks in the task agnostic inference. We empirically show that we can achieve a better performance than several state-of-the-art methods for continual learning by building on the top of selected representation learned by SAM. We also show the role of the meta-attention mechanism in boosting informative features corresponding to the input data and identifying the correct target in the task agnostic inference. Finally, we demonstrate that popular existing continual learning methods gain a performance boost when they adopt SAM as a starting point.
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its variants. However, these algorithms have to implement various strategies, such as memory buffers or replay, to overcome well-known shortcomings of stochastic gradient descent methods in terms of stability, greed, and short-term memory. To that end, we develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation to enable input processing over data streams and online learning. Next, we address the challenge of hyperparameter selection for tasks that are not known in advance by implementing transfer metalearning: using a Bayesian optimization to explore a design space spanning multiple local learning rules and their hyperparameters, we identify high performing configurations in classical single task online learning and we transfer them to continual learning tasks with task-similarity considerations. We demonstrate the efficacy of our approach on both single task and continual learning setting. For the single task learning setting, we demonstrate superior performance over other local learning approaches on the MNIST, Fashion MNIST, and CIFAR-10 datasets. Using high performing configurations metalearned in the single task learning setting, we achieve superior continual learning performance on Split-MNIST, and Split-CIFAR-10 data as compared with other memory-constrained learning approaches, and match that of the state-of-the-art memory-intensive replay-based approaches.
A central challenge in developing versatile machine learning systems is catastrophic forgetting: a model trained on tasks in sequence will suffer significant performance drops on earlier tasks. Despite the ubiquity of catastrophic forgetting, there is limited understanding of the underlying process and its causes. In this paper, we address this important knowledge gap, investigating how forgetting affects representations in neural network models. Through representational analysis techniques, we find that deeper layers are disproportionately the source of forgetting. Supporting this, a study of methods to mitigate forgetting illustrates that they act to stabilize deeper layers. These insights enable the development of an analytic argument and empirical picture relating the degree of forgetting to representational similarity between tasks. Consistent with this picture, we observe maximal forgetting occurs for task sequences with intermediate similarity. We perform empirical studies on the standard split CIFAR-10 setup and also introduce a novel CIFAR-100 based task approximating realistic input distribution shift.