HINT: Hypernetwork approach to training weight interval regions in continual learning

Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing interval constraints on the neural network parameter space. Unfortunately, InterContiNet training is challenging due to the high dimensionality of the weight space, making intervals difficult to manage. To address this issue, we introduce HINT, a technique that employs interval arithmetic within the embedding space and utilizes a hypernetwork to map these intervals to the parameter space of the target network. We train interval embeddings for consecutive tasks and train a hypernetwork to transform these embeddings into weights of the target network. An embedding for a given task is trained along with the hypernetwork, preserving the response of the target network for the previous task embeddings. Interval arithmetic works with lower-dimensional embedding space rather than directly preparing intervals in a high-dimensional weight space. Furthermore, HINT maintains the guarantee of not forgetting. At the end of the training, we can choose one universal embedding to produce a single network dedicated to all tasks. In such a framework, we can utilize one set of weights. HINT obtains significantly better results than InterContiNet and gives SOTA results on several benchmarks.