Neural Lineage

TL;DR

This paper introduces neural lineage detection, a novel task to identify parent models of fine-tuned neural networks, proposing both a similarity-based and a learning-based approach, validated across various models and settings.

Contribution

It presents the first methods for neural lineage detection, including a learning-free similarity approach and a learning-based transformer model, advancing model lineage tracing capabilities.

Findings

Both methods outperform baselines in various settings

The approaches can trace cross-generational lineage

Methods are adaptable to different visual models

Abstract

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.