对比损失作为全局上位性的广义模型
Contrastive losses as generalized models of global epistasis
AI总结：
本文提出利用监督对比损失（如Bradley-Terry损失）来提取全局上位性模型中的稀疏潜在函数，解决了MSE损失在非线性变换下学习效率低下的问题，并在基准任务上实现了持续提升的性能。
摘要：
适合度函数将生物序列的大型组合空间映射到感兴趣的属性。从实验数据中推断这些多模态函数是现代蛋白质工程的核心任务。全局上位性模型是一类有效且基于物理的模型，用于从观测数据中估计适合度函数。这些模型假设一个稀疏的潜在函数通过单调非线性变换来产生可测量的适合度。在这里，我们证明了最小化监督对比损失函数（如 Bradley-Terry 损失）是一种简单且灵活的技术，用于提取全局上位性所隐含的稀疏潜在函数。我们通过适合度-上位性不确定性原理论证，全局上位性模型中的非线性可以产生不包含稀疏表示的观测适合度函数，因此在使用均方误差（MSE）损失（一种常见做法）从观测中学习时可能效率低下。我们表明，对比损失能够在 MSE 无效的情况下从有限数据中准确估计排序函数，并通过证明对比损失函数在基准任务上产生持续提升的性能来验证这一见解的实用价值。
英文摘要：
Fitness functions map large combinatorial spaces of biological sequences to properties of interest. Inferring these multimodal functions from experimental data is a central task in modern protein engineering. Global epistasis models are an effective and physically-grounded class of models for estimating fitness functions from observed data. These models assume that a sparse latent function is transformed by a monotonic nonlinearity to emit measurable fitness. Here we demonstrate that minimizing supervised contrastive loss functions, such as the Bradley-Terry loss, is a simple and flexible technique for extracting the sparse latent function implied by global epistasis. We argue by way of a fitness-epistasis uncertainty principle that the nonlinearities in global epistasis models can produce observed fitness functions that do not admit sparse representations, and thus may be inefficient to learn from observations when using a Mean Squared Error (MSE) loss (a common practice). We show that contrastive losses are able to accurately estimate a ranking function from limited data even in regimes where MSE is ineffective and validate the practical utility of this insight by demonstrating that contrastive loss functions result in consistently improved performance on benchmark tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
