SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10951 · 2022

Hyper-Representations for Pre-Training and Transfer Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.10951")
get_code_for_paper("2207.10951")
have("2207.10951")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.10951.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.10951.svg)](https://syntology.ai/paper/2207.10951)

Connect an agent — have() is free.