Direct Preference Optimization (DPO) is an effective approach for aligning protein language models with experimental design goals. However, DPO faces a scalability bottleneck: the number of possible training pairs grows quadratically with the number of labeled sequences, leading to prohibitive training times even for modestly sized datasets. We introduce g-DPO, a framework that (i) uses sequence space clustering to prune redundant pairs while preserving training signal, and (ii) amortizes likelihood computations with group-based approximations. Across three protein engineering tasks, g-DPO maintains in silico and in vitro performance that is statistically indistinguishable from standard DPO, while converging 1.7x to 5.4x times faster, with speedups that scale with dataset size and the structure of the underlying mutational landscape.
@article{arxiv.2510.19474,
title = {g-DPO: Scalable Preference Optimization for Protein Language Models},
author = {Constance Ferragu and Jonathan D. Ziegler and Nicolas Deutschmann and Arthur Lindoulsi and Eli Bixby and Cradle ML Team},
journal= {arXiv preprint arXiv:2510.19474},
year = {2025}
}
Comments
Accepted at two workshops: FM4LS NeurIPS 2025 (https://nips2025fm4ls.github.io/pages/accepted-paper.html) and MLSB in Copenhagen EurIPS 2025