Feature-based Graph Attention Networks Improve Online Continual Learning
This work addresses the problem of adapting models to new data while retaining knowledge in dynamic environments, which is crucial for real-world applications, though it appears incremental as it builds on existing GAT and continual learning techniques.
The paper tackles online continual learning for image classification by introducing a framework based on Graph Attention Networks (GATs) that captures contextual relationships and uses rehearsal memory duplication, achieving superior performance on benchmark datasets like SVHN, CIFAR10, CIFAR100, and MiniImageNet compared to state-of-the-art methods.
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic environments and evolving data distributions. Traditional approaches predominantly employ Convolutional Neural Networks, which are limited to processing images as grids and primarily capture local patterns rather than relational information. Although the emergence of transformer architectures has improved the ability to capture relationships, these models often require significantly larger resources. In this paper, we present a novel online continual learning framework based on Graph Attention Networks (GATs), which effectively capture contextual relationships and dynamically update the task-specific representation via learned attention weights. Our approach utilizes a pre-trained feature extractor to convert images into graphs using hierarchical feature maps, representing information at varying levels of granularity. These graphs are then processed by a GAT and incorporate an enhanced global pooling strategy to improve classification performance for continual learning. In addition, we propose the rehearsal memory duplication technique that improves the representation of the previous tasks while maintaining the memory budget. Comprehensive evaluations on benchmark datasets, including SVHN, CIFAR10, CIFAR100, and MiniImageNet, demonstrate the superiority of our method compared to the state-of-the-art methods.