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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The performance of algorithms for neural architecture search strongly depends on the parametrization of the search space. We use contrastive learning to identify networks across different initializations based on their data Jacobians, and automatically produce the first architecture embeddings independent from the parametrization of the search space. Using our contrastive embeddings, we show that traditional black-box optimization algorithms, without modification, can reach state-of-the-art performance in Neural Architecture Search. As our method provides a unified embedding space, we perform for the first time transfer learning between search spaces. Finally, we show the evolution of embeddings during training, motivating future studies into using embeddings at different training stages to gain a deeper understanding of the networks in a search space.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2102.04208")
get_code_for_paper("2102.04208")
have("2102.04208")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2102.04208.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2102.04208)
Connect an agent — have() is free.