Hyper-Representations for Pre-Training and Transfer Learning
This work addresses the challenge of knowledge aggregation from model zoos for researchers and practitioners in machine learning, though it appears incremental as it builds on prior hyper-representation methods.
The authors tackled the problem of generating new neural network models from a model zoo by extending hyper-representations for generative use, achieving models that outperform conventional transfer learning baselines.
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an autoencoder trained on a model zoo was able to learn a hyper-representation, which captures intrinsic and extrinsic properties of the models in the zoo. In this work, we extend hyper-representations for generative use to sample new model weights as pre-training. We propose layer-wise loss normalization which we demonstrate is key to generate high-performing models and a sampling method based on the empirical density of hyper-representations. The models generated using our methods are diverse, performant and capable to outperform conventional baselines for transfer learning. Our results indicate the potential of knowledge aggregation from model zoos to new models via hyper-representations thereby paving the avenue for novel research directions.