Importance-aware Co-teaching for Offline Model-based Optimization

Ye Yuan, Willie Neiswanger, Xue Liu, Zixuan Liu, Sam Chen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• stevenyuan666/importance-aware-co-teaching — marked official in Papers with Code; named in the paper

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

Abstract

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent, where a proxy model is trained on the offline dataset and then used to optimize the design. This method suffers from an out-of-distribution issue, where the proxy is not accurate for unseen designs. To mitigate this issue, we explore using a pseudolabeler to generate valuable data for fine-tuning the proxy. Specifically, we propose Importance-aware Co-Teaching for Offline Model-based Optimization (ICT). This method maintains three symmetric proxies with their mean ensemble as the final proxy, and comprises two steps. The first step is pseudo-label-driven co-teaching. In this step, one proxy is iteratively selected as the pseudo-labeler for designs near the current optimization point, generating pseudo-labeled data. Subsequently, a co-teaching process identifies small-loss samples as valuable data and exchanges them between the other two proxies for fine-tuning, promoting knowledge transfer. This procedure is repeated three times, with a different proxy chosen as the pseudolabeler each time, ultimately enhancing the ensemble performance. To further improve accuracy of pseudo-labels, we perform a secondary step of meta-learningbased sample reweighting, which assigns importance weights to samples in the pseudo-labeled dataset and updates them via meta-learning. ICT achieves state-ofthe-art results across multiple design-bench tasks, achieving the best mean rank of 3.1 and median rank of 2, among 15 methods. Our source code can be found here.

For agents

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

get_harvested_code_for_paper("2309.11600")
get_code_for_paper("2309.11600")
have("2309.11600")

Connect an agent — have() is free.