Catastrophic forgetting is when a neural network loses previously learnt information after learning a new task sequentially. Avoiding catastrophic forgetting could reduce the resources necessary to update neural networks. Recently, Kolmogorov–Arnold Networks (KAN) gained the community's attention as preliminary experiments suggest KAN avoid catastrophic forgetting. KAN replace neural network edges with learnable B-splines and sum incoming edges in nodes. Proponents of KAN argue they avoid forgetting, are more accurate, are interpretable, and use fewer parameters. Our work investigates the claims that KAN avoid catastrophic forgetting, finding that they fail to do so on more complex datasets containing features that overlap between tasks. We give a simple explanation as to why and how KAN catastrophically forget. Motivated by evidence suggesting KAN are superior for symbolic regression, we augment KAN in the same ways as multilayer perceptron (MLP) to perform continual learning tasks, making special accommodations to support KAN. Our experiments found that unmodified KAN often forget more than MLP, but KAN can be better than MLP when combined with continual learning strategies. We aim to highlight some of the current shortcomings and strengths associated with KAN for continual learning.

Continual learning aims to create artificial neural networks capable of accumulating knowledge and skills through incremental training on a sequence of tasks. The main challenge of continual learning is catastrophic interference, wherein new knowledge overrides or interferes with past knowledge, leading to forgetting. An associated issue is the problem of learning "cross-task knowledge," where models fail to acquire and retain knowledge that helps differentiate classes across task boundaries. A common solution to both problems is "replay," where a limited buffer of past instances is utilized to learn cross-task knowledge and mitigate catastrophic interference. However, a notable drawback of these methods is their tendency to overfit the limited replay buffer. In contrast, our proposed solution, SurpriseNet, addresses catastrophic interference by employing a parameter isolation method and learning cross-task knowledge using an auto-encoder inspired by anomaly detection. SurpriseNet is applicable to both structured and unstructured data, as it does not rely on image-specific inductive biases. We have conducted empirical experiments demonstrating the strengths of SurpriseNet on various traditional vision continual-learning benchmarks, as well as on structured data datasets. Source code made available at https://doi.org/10.5281/zenodo.8247906 and https://github.com/tachyonicClock/SurpriseNet-CIKM-23

Balancing the stability-plasticity dilemma is an omnipresent challenge in continual learning. The dilemma is that the ability of a model to learn new knowledge (plasticity) comes at the expense of the ability to remember past knowledge (stability) and vice versa. Some continual learning algorithms incorporate a constant hyper-parameter to control this trade-off. We argue that the trade-off should be dynamically tuned rather than kept constant. We propose a method to dynamically balance stability and plasticity in a semi-online and fully online manner. Our method is applicable to a range of underlying regularisation based strategies and class incremental problems. Our experiments in three continual learning benchmarks suggest that dynamic stability tuning methods can improve accuracy and decrease forgetting of continual learning strategies throughout their lifetime.

Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to approximate the observed input distributions over time with a small memory and revisit them later to avoid forgetting. Despite their strong empirical performance, rehearsal methods still suffer from a poor approximation of past data’s loss landscape with memory samples. This paper revisits the rehearsal dynamics in online settings. We provide theoretical insights on the inherent memory overfitting risk from the viewpoint of biased and dynamic empirical risk minimization, and examine the merits and limits of repeated rehearsal.Inspired by our analysis, a simple and intuitive baseline, repeated augmented rehearsal (RAR), is designed to address the underfitting-overfitting dilemma of online rehearsal. Surprisingly, across four rather different OCL benchmarks,this simple baseline outperforms vanilla rehearsal by 9\%-17\% and also significantly improves the state-of-the-art rehearsal-based methods MIR, ASER, and SCR. We also demonstrate that RAR successfully achieves an accurate approximation of the loss landscape of past data and high-loss ridge aversion in its learning trajectory. Extensive ablation studies are conducted to study the interplay between repeated and augmented rehearsal, and reinforcement learning (RL) is applied to dynamically adjust the hyperparameters of RAR to balance the stability-plasticity trade-off online.