Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental


Konstantin Schürholt, Dimche Kostadinov, Damian Borth


Self-Supervised Learning (SSL) has been shown to learn useful and information-preserving representations. Neural Networks (NNs) are widely applied, yet their weight space is still not fully understood. Therefore, we propose to use SSL to learn hyper-representations of the weights of populations of NNs. To that end, we introduce domain specific data augmentations and an adapted attention architecture. Our empirical evaluation demonstrates that self-supervised representation learning in this domain is able to recover diverse NN model characteristics. Further, we show that the proposed learned representations outperform prior work for predicting hyper-parameters, test accuracy, and generalization gap as well as transfer to out-of-distribution settings.