Improved Generalization of Weight Space Networks via Augmentations

Aviv Shamsian, Aviv Navon, David W. Zhang, Yan Zhang, Ethan Fetaya, Gal Chechik, Haggai Maron

Research output: Contribution to journalConference articlepeer-review

Abstract

Learning in deep weight spaces (DWS), where neural networks process the weights of other neural networks, is an emerging research direction, with applications to 2D and 3D neural fields (INRs, NeRFs), as well as making inferences about other types of neural networks. Unfortunately, weight space models tend to suffer from substantial overfitting. We empirically analyze the reasons for this overfitting and find that a key reason is the lack of diversity in DWS datasets. While a given object can be represented by many different weight configurations, typical INR training sets fail to capture variability across INRs that represent the same object. To address this, we explore strategies for data augmentation in weight spaces and propose a MixUp method adapted for weight spaces. We demonstrate the effectiveness of these methods in two setups. In classification, they improve performance similarly to having up to 10 times more data. In self-supervised contrastive learning, they yield substantial 5-10% gains in downstream classification.

Original languageEnglish
Pages (from-to)44378-44393
Number of pages16
JournalProceedings of Machine Learning Research
Volume235
StatePublished - 2024
Event41st International Conference on Machine Learning, ICML 2024 - Vienna, Austria
Duration: 21 Jul 202427 Jul 2024

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Cite this