Transfer Learning via Test-Time Neural Networks Aggregation
This work addresses the issue of catastrophic forgetting and training overhead in transfer learning for machine learning practitioners, though it appears incremental as it builds on existing aggregation ideas.
The paper tackles the problem of domain shift in deep neural networks by proposing a transfer learning approach that aggregates dataset-specific networks at test time without additional training, achieving comparable performance to baseline methods.
It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution due to the domain shift. In order to tackle this known issue, several transfer learning approaches have been proposed, where the knowledge of a trained model is transferred into another to improve performance with different data. However, most of these approaches require additional training steps, or they suffer from catastrophic forgetting that occurs when a trained model has overwritten previously learnt knowledge. We address both problems with a novel transfer learning approach that uses network aggregation. We train dataset-specific networks together with an aggregation network in a unified framework. The loss function includes two main components: a task-specific loss (such as cross-entropy) and an aggregation loss. The proposed aggregation loss allows our model to learn how trained deep network parameters can be aggregated with an aggregation operator. We demonstrate that the proposed approach learns model aggregation at test time without any further training step, reducing the burden of transfer learning to a simple arithmetical operation. The proposed approach achieves comparable performance w.r.t. the baseline. Besides, if the aggregation operator has an inverse, we will show that our model also inherently allows for selective forgetting, i.e., the aggregated model can forget one of the datasets it was trained on, retaining information on the others.