Skip to yearly menu bar Skip to main content


Poster

Neural Lineage

Runpeng Yu · Xinchao Wang

Arch 4A-E Poster #82
[ ] [ Paper PDF ]
[ Poster
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT
 
Oral presentation: Orals 2B Deep learning architectures and techniques
Wed 19 Jun 1 p.m. PDT — 2:30 p.m. PDT

Abstract:

Given a well-behaved neural network, is possibleto 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, effectively identifying not only parent models but also their ancestors.

Chat is not available.