arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.10555cs.LGstat.ML
收藏

MLDS:一个用于神经网络权空间分析的数据集

MLDS: A Dataset for Weight-Space Analysis of Neural Networks

UMBC(马里兰大学巴尔的摩县分校)

John Clemens

摘要:

神经网络是解决各种复杂现实问题的强大模型。然而,训练的随机性和典型神经模型中的大量参数使得它们难以通过检查进行评估。研究表明,这种不透明性可以隐藏潜在的不良行为,无论是来自代表性差的训练数据还是通过恶意意图来破坏网络的行为,并且这种行为很难通过传统的间接评估标准(如损失)来检测。因此,现在是时候探索通过其结构和权重来评估训练好的神经模型的直接方法了。在本文中,我们提出了MLDS,一个新的数据集,由数千个经过训练的神经网络精心控制的参数,并通过全球志愿者为基础的分布式计算平台生成。该数据集使我们能够对模型到模型和模型到训练数据的关系有新的见解。我们使用这个数据集来显示具有相同训练数据的权重空间中的模型的聚类,以及即使对训练数据进行很小的更改也会在权重空间中产生有意义的发散,这表明权重空间分析是评估神经网络的一种可行且有效的损失替代方案。

英文摘要:

Neural networks are powerful models that solve a variety of complex real-world problems. However, the stochastic nature of training and large number of parameters in a typical neural model makes them difficult to evaluate via inspection. Research shows this opacity can hide latent undesirable behavior, be it from poorly representative training data or via malicious intent to subvert the behavior of the network, and that this behavior is difficult to detect via traditional indirect evaluation criteria such as loss. Therefore, it is time to explore direct ways to evaluate a trained neural model via its structure and weights. In this paper we present MLDS, a new dataset consisting of thousands of trained neural networks with carefully controlled parameters and generated via a global volunteer-based distributed computing platform. This dataset enables new insights into both model-to-model and model-to-training-data relationships. We use this dataset to show clustering of models in weight-space with identical training data and meaningful divergence in weight-space with even a small change to the training data, suggesting that weight-space analysis is a viable and effective alternative to loss for evaluating neural networks.

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。

↑