Neural Lineage
This addresses the problem of model provenance and accountability in machine learning, but it is incremental as it builds on existing similarity metrics and fine-tuning concepts.
The paper tackles the problem of identifying lineage relationships between neural networks, specifically determining which parent model a child model was fine-tuned from, and shows that their proposed learning-free and learning-based methods outperform baselines in various settings and can trace cross-generational lineage.
Given a well-behaved neural network, is possible to identify its parent, based on which it was tuned? In this paper, we introduce a novel task known as neural lineage detection, aiming at discovering lineage relationships between parent and child models. Specifically, from a set of parent models, neural lineage detection predicts which parent model a child model has been fine-tuned from. We propose two approaches to address this task. (1) For practical convenience, we introduce a learning-free approach, which integrates an approximation of the finetuning process into the neural network representation similarity metrics, leading to a similarity-based lineage detection scheme. (2) For the pursuit of accuracy, we introduce a learning-based lineage detector comprising encoders and a transformer detector. Through experimentation, we have validated that our proposed learning-free and learning-based methods outperform the baseline in various learning settings and are adaptable to a variety of visual models. Moreover, they also exhibit the ability to trace cross-generational lineage, identifying not only parent models but also their ancestors.